© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8493
    Prev
    Next
    INDEX
    Explanations

    foreign language grammatical endings

    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
     actuel
    0.35
     பேர்
    0.32
    atrical
    0.32
     étudiant
    0.32
     illustrious
    0.31
     absoluta
    0.31
    '
    0.31
     individus
    0.31
     wichtigsten
    0.30
    ers
    0.29
    POSITIVE LOGITS
     and
    0.34
    UP
    0.29
    and
    0.28
    {
    0.28
    ON
    0.26
     slimming
    0.26
    AND
    0.25
     or
    0.24
    ла
    0.24
    ド
    0.23
    Activations Density 0.120%

    No Known Activations