© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2393
    Prev
    Next
    INDEX
    Explanations

    CS, CSI, CSP, CSA, CSF

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

    The neuron activates on numeric tokens and digits (i.e. numbers and number sequences).

    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
    歇
    -0.71
    淩
    -0.69
     tört
    -0.69
     király
    -0.68
     bailarina
    -0.68
    óval
    -0.67
    壽
    -0.66
     cocco
    -0.66
    äj
    -0.65
    edipus
    -0.65
    POSITIVE LOGITS
     CS
    5.00
     cs
    4.53
    CS
    4.47
    cs
    3.98
     Cs
    3.50
     CSA
    3.38
     CSF
    3.17
    Cs
    3.14
     CSP
    3.02
    CSP
    2.97
    Activations Density 0.062%

    No Known Activations