© 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. 169464
    Prev
    Next
    INDEX
    Explanations

    or see or read

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

    how to best support you

    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
     丿
    0.48
    𝗂
    0.48
     монасты
    0.46
    atoti
    0.46
    ᔕ
    0.46
    urados
    0.45
    ѡ
    0.44
    subMenu
    0.44
    kla
    0.43
    rugula
    0.43
    POSITIVE LOGITS
    -
    0.56
     slightest
    0.50
    Anything
    0.50
    ه
    0.49
    Any
    0.47
     dieser
    0.46
     anything
    0.45
    任何
    0.45
     dàn
    0.45
     ANYTHING
    0.44
    Activations Density 0.002%

    No Known Activations