© 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. 35901
    Prev
    Next
    INDEX
    Explanations

    all rows

    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
    微博
    0.47
    efois
    0.44
    loans
    0.41
    PTV
    0.41
     escánd
    0.40
    ཋ
    0.40
    μοι
    0.39
     recipro
    0.38
    㛣
    0.38
     گوئیاں
    0.38
    POSITIVE LOGITS
    原来的
    0.49
     previous
    0.44
     original
    0.43
     остальных
    0.43
     next
    0.42
     storing
    0.42
     the
    0.42
     timer
    0.42
     BH
    0.42
    ver
    0.42
    Activations Density 0.000%

    No Known Activations