© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47783
    Prev
    Next
    INDEX
    Explanations

    image references

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens—digits or number sequences such as line numbers, image dimensions, dollar amounts, or other numeric literals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }$,
    -0.94
     but
    -0.87
    erapeutic
    -0.85
     sehingga
    -0.84
    emiah
    -0.84
    之道
    -0.83
    }}$,
    -0.82
     which
    -0.81
     articles
    -0.79
    仍
    -0.79
    POSITIVE LOGITS
    IMG
    2.63
     IMG
    2.30
    Attachment
    2.05
    image
    1.94
    Untitled
    1.88
    DSC
    1.88
    attachment
    1.80
     img
    1.71
    img
    1.71
     Attachment
    1.69
    Activations Density 0.028%

    No Known Activations