© 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. 179418
    Prev
    Next
    INDEX
    Explanations

    concrete entities and specific terms

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

    relationships, acids, partially, Draw, Handle, triangle

    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
    ))],
    0.46
     রোগীর
    0.45
    കര
    0.43
     reparación
    0.41
    openstreetmap
    0.41
    +//
    0.41
     clin
    0.40
    カー
    0.39
    れる
    0.39
     শুক্র
    0.39
    POSITIVE LOGITS
    ਨ
    0.48
     erity
    0.48
     parti
    0.46
     Vla
    0.46
    鞠
    0.46
    雩
    0.45
     särsk
    0.45
     ਇੱਕ
    0.45
     väldigt
    0.44
    屒
    0.44
    Activations Density 0.001%

    No Known Activations