© 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. 161315
    Prev
    Next
    INDEX
    Explanations

    to repair, use, testing

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

    saving state or data

    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
     posséd
    0.48
    链路
    0.46
     পরিবেশে
    0.46
     vasculaire
    0.45
     possède
    0.45
    捣
    0.43
     生命
    0.43
     ዓ
    0.43
     cancé
    0.43
     bencana
    0.43
    POSITIVE LOGITS
    allar
    0.44
    eref
    0.43
    adjust
    0.43
    ify
    0.42
    avid
    0.42
    ay
    0.42
    ive
    0.41
    aj
    0.41
    ival
    0.41
    any
    0.40
    Activations Density 0.001%

    No Known Activations