© 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-65K
    7. 7917
    Prev
    Next
    INDEX
    Explanations

    all subscriptions / Temperature

    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_65k_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
    лайн
    0.55
     pronto
    0.51
     направ
    0.49
     કરીએ
    0.48
     ટ
    0.47
     ફક્ત
    0.47
     تباہ
    0.46
     dejamos
    0.46
    splitted
    0.46
     undead
    0.46
    POSITIVE LOGITS
    UC
    0.48
    rme
    0.47
    ULT
    0.46
    INS
    0.46
    <start_of_image>
    0.44
    CS
    0.43
    Wat
    0.43
     subscriptions
    0.43
    AF
    0.42
    慢
    0.42
    Activations Density 0.011%

    No Known Activations