© 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. 32930
    Prev
    Next
    INDEX
    Explanations

    analogue/analytical terms

    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
     in
    0.43
    itism
    0.38
    ber
    0.38
    tek
    0.37
    在
    0.37
    cles
    0.37
    hom
    0.37
    rogens
    0.36
    abs
    0.36
    de
    0.36
    POSITIVE LOGITS
     প্রজাত
    0.46
    歌詞
    0.44
    Ẽ
    0.44
     analges
    0.44
    Attenuation
    0.44
    ዻ
    0.43
     보도록
    0.43
    ربي
    0.43
    PlayerDataCache
    0.43
     نبدا
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.