© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 22083
    Prev
    Next
    INDEX
    Explanations

    there until failing continuing

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

    SQL JOIN queries

    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
    amak
    0.50
     경우가
    0.50
     종
    0.48
    asam
    0.48
    alba
    0.48
     볼
    0.47
     청
    0.47
     па
    0.47
     화
    0.46
    elle
    0.46
    POSITIVE LOGITS
    ленных
    0.49
     বহুদিন
    0.46
     $$$
    0.45
    ες
    0.45
    رت
    0.45
     Dating
    0.44
     Veranst
    0.43
     assuring
    0.43
    goto
    0.43
    গি
    0.43
    Activations Density 0.000%

    No Known Activations