© 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. 28510
    Prev
    Next
    INDEX
    Explanations

    providing descriptions and alternatives

    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
    0
    0.62
    -
    0.52
    zione
    0.51
    1
    0.50
    is
    0.50
    ol
    0.50
    op
    0.49
    of
    0.49
    um
    0.49
     ripe
    0.49
    POSITIVE LOGITS
     альбом
    0.54
    ्यूड
    0.53
    .|__
    0.51
     kttt
    0.51
     మధ్య
    0.50
     turkeys
    0.50
    𒀜
    0.50
     tüket
    0.50
     actualizaciones
    0.49
     shepherds
    0.47
    Activations Density 0.000%

    No Known Activations