© 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. 61940
    Prev
    Next
    INDEX
    Explanations

    matte nails, tumor growth

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

    wanting to be integer

    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
    ش
    0.58
    ج
    0.49
    س
    0.49
    es
    0.48
     وك
    0.48
    kc
    0.46
    حسن
    0.46
    agos
    0.43
    ด
    0.43
    servers
    0.43
    POSITIVE LOGITS
     женщина
    0.51
    ালিক
    0.50
     pemimpin
    0.50
    équip
    0.50
     компози
    0.48
     женщины
    0.47
     طریقے
    0.47
     maaaring
    0.47
     üçüncü
    0.47
    Exponential
    0.47
    Activations Density 0.000%

    No Known Activations