© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217441
    Prev
    Next
    INDEX
    Explanations

    pinterest design, difficult topics, stewards

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

    during pregnancy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     activations
    0.49
    Arkansas
    0.46
    𝑁
    0.46
    écution
    0.46
    Robinson
    0.45
    ServiceID
    0.44
    _,
    0.44
    ॅ
    0.44
    א
    0.44
    Activation
    0.44
    POSITIVE LOGITS
     ór
    0.50
     Padd
    0.47
     كر
    0.47
     ISD
    0.47
     pomiesz
    0.47
     khi
    0.46
     plaats
    0.46
     जगह
    0.46
     শাস্ত্র
    0.46
     Solana
    0.46
    Activations Density 0.000%

    No Known Activations