© 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. 181379
    Prev
    Next
    INDEX
    Explanations

    by or through information

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

    formal or technical instructions

    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
     critic
    0.46
    евского
    0.45
     Städte
    0.42
    ('@
    0.42
    koliko
    0.41
    ֨
    0.40
     RTX
    0.40
    ELEMENT
    0.40
    呂
    0.40
    ટું
    0.39
    POSITIVE LOGITS
     ద్వారా
    0.53
    码
    0.52
     दरवा
    0.49
     μέσω
    0.49
    夫妇
    0.47
     দ
    0.46
     σ
    0.46
     tarafından
    0.45
     объеди
    0.45
    rą
    0.45
    Activations Density 0.001%

    No Known Activations