© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2188
    Prev
    Next
    INDEX
    Explanations

    making crafts and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nya
    3.75
    t
    2.82
    ى
    2.81
    ر
    2.71
    ting
    2.64
    ும்
    2.60
    പ്പം
    2.58
    ই
    2.55
    డ్డు
    2.54
    ことができる
    2.54
    POSITIVE LOGITS
    leine
    3.12
    ငန်း
    2.97
     frente
    2.74
    an
    2.44
     sta
    2.41
    le
    2.40
    {}".
    2.36
    к
    2.32
     landfall
    2.30
    ྥ
    2.30
    Activations Density 0.034%

    No Known Activations