© 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. 184496
    Prev
    Next
    INDEX
    Explanations

    phrases and common subsequent words

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

    App or product descriptions

    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
     intestino
    0.53
    nosť
    0.47
    ('#
    0.45
     bombed
    0.45
    仿真
    0.44
    ñón
    0.44
    ĥ
    0.43
    abbing
    0.43
     вперед
    0.43
    的高
    0.43
    POSITIVE LOGITS
    c
    0.59
    v
    0.58
     Kod
    0.47
     Pov
    0.44
     වශ
    0.44
    al
    0.44
    Kod
    0.43
     Genel
    0.43
    et
    0.43
     Code
    0.43
    Activations Density 0.001%

    No Known Activations