Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 143777
    Prev
    Next
    INDEX
    Explanations

    truly predictive

    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
     Incent
    0.53
     चुनौ
    0.51
     incentives
    0.51
     انتظ
    0.50
     车
    0.50
     डांस
    0.46
     హీరో
    0.45
     요청
    0.44
     छात्र
    0.44
    يسي
    0.44
    POSITIVE LOGITS
     (+
    0.47
    군요
    0.46
     (=
    0.44
     sua
    0.42
     suas
    0.41
    matism
    0.41
     malam
    0.40
    ])));
    0.40
    certain
    0.40
     (*
    0.39
    Activations Density 0.004%

    No Known Activations