© 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. 89239
    Prev
    Next
    INDEX
    Explanations

    daughter of, reason for, invalid or, Exchange plans

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

    in 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
     প্রহ
    0.48
    keyup
    0.46
    KeyListener
    0.46
    来て
    0.46
     χρώ
    0.44
     nöt
    0.43
     bús
    0.43
    秪
    0.43
    😤
    0.42
    狷
    0.40
    POSITIVE LOGITS
    nvarchar
    0.47
    e
    0.47
    Bindings
    0.46
    BLEND
    0.46
    o
    0.45
    ्ला
    0.45
    á
    0.45
     Database
    0.44
     encontro
    0.44
    ca
    0.44
    Activations Density 0.001%

    No Known Activations