© 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. 2758
    Prev
    Next
    INDEX
    Explanations

    public action or entity

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

    human thought and language

    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
     the
    0.42
     The
    0.37
     were
    0.37
    在
    0.36
     थे
    0.35
     \
    0.34
     JUN
    0.33
     LHS
    0.33
     are
    0.32
    的
    0.32
    POSITIVE LOGITS
     crusade
    0.38
    向け
    0.33
     microcosm
    0.32
     pastime
    0.31
     martyr
    0.29
     nobleman
    0.29
     dilemma
    0.28
    жете
    0.28
     penchant
    0.28
     manifesto
    0.28
    Activations Density 0.181%

    No Known Activations