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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60919
    Prev
    Next
    INDEX
    Explanations

    citations and references

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

    The neuron flags inline scholarly citation markers (bracketed reference numbers and their surrounding bracket/caret symbols).

    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
    }$.
    -0.91
    anmoins
    -0.88
    Meanwhile
    -0.86
     Meanwhile
    -0.85
     }}"></
    -0.84
     նաև
    -0.83
    ratory
    -0.82
     حرف
    -0.82
     جواب
    -0.82
    色々と
    -0.82
    POSITIVE LOGITS
    fishing
    0.86
     depth
    0.85
     Moul
    0.83
    aminan
    0.79
     boxe
    0.79
    CUP
    0.78
    DEPTH
    0.78
    
    0.77
    "+"
    0.77
    depth
    0.76
    Activations Density 0.028%

    No Known Activations