© 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. 39006
    Prev
    Next
    INDEX
    Explanations

    example language

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

    direct or directly

    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
    印象
    0.48
    up
    0.47
    薨
    0.46
    ímp
    0.45
    病院
    0.44
    ка
    0.44
    ép
    0.44
    ギ
    0.43
    }}=-
    0.43
    意
    0.43
    POSITIVE LOGITS
     vettore
    0.59
     teha
    0.53
     Misalnya
    0.52
     esimerkiksi
    0.51
     xpath
    0.50
     Например
    0.50
     regioni
    0.49
     placé
    0.49
     misalkan
    0.49
     placée
    0.48
    Activations Density 0.000%

    No Known Activations