© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11331
    Prev
    Next
    INDEX
    Explanations

    ability to do things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    㩴
    2.29
     currentDate
    2.24
    ী
    2.24
     traps
    2.24
     bianca
    2.19
     hick
    2.19
     बैठ
    2.16
     हुँ
    2.14
    愉
    2.13
    ங்கிணை
    2.13
    POSITIVE LOGITS
    ﺏ
    2.43
    La
    2.30
    qx
    2.11
     La
    2.09
    做到
    2.01
    CLOSE
    1.99
    Los
    1.97
    يم
    1.95
     la
    1.93
     Fine
    1.93
    Activations Density 0.040%

    No Known Activations