© 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. 29212
    Prev
    Next
    INDEX
    Explanations

    specific word pairs

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

    API, molecules, often, short

    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
     ν
    0.46
     ChIP
    0.45
     mitigated
    0.44
     вступи
    0.44
    ība
    0.44
     lager
    0.43
     σύ
    0.42
     Goldman
    0.42
     circost
    0.41
     granting
    0.41
    POSITIVE LOGITS
     mue
    0.53
    Ali
    0.48
    Primero
    0.47
    0
    0.46
    ۰
    0.45
     asupra
    0.44
    wave
    0.42
     рыб
    0.42
    Ò
    0.41
    راه
    0.41
    Activations Density 0.000%

    No Known Activations