© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18212
    Prev
    Next
    INDEX
    Explanations

    specific nouns or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à
    0.44
    ل
    0.41
    -
    0.39
    the
    0.38
    >
    0.38
     The
    0.38
     I
    0.37
    The
    0.36
    れ
    0.35
    le
    0.35
    POSITIVE LOGITS
     постоянно
    0.38
     proffered
    0.37
     injected
    0.36
     стомато
    0.36
     tablero
    0.35
     decidedly
    0.35
     rab
    0.34
    jenigen
    0.34
     socalled
    0.34
     moisturizer
    0.34
    Activations Density 0.049%

    No Known Activations