© 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. 245155
    Prev
    Next
    INDEX
    Explanations

    LLC, perfect, beam

    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
    頬
    0.48
     грав
    0.46
    룀
    0.43
    र्चा
    0.42
    に向
    0.42
    虐
    0.42
    経
    0.41
     photovoltaic
    0.41
     degradation
    0.40
    颠
    0.40
    POSITIVE LOGITS
    liği
    0.55
    nn
    0.50
    zt
    0.49
     komple
    0.47
     Sous
    0.47
    StoreException
    0.47
    tedy
    0.46
    zne
    0.46
     آتے
    0.46
    zzz
    0.46
    Activations Density 0.001%

    No Known Activations