© 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. 40-GEMMASCOPE-2-RES-262K
    7. 205322
    Prev
    Next
    INDEX
    Explanations

    way to/of, functionally behave, Steam Flow

    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_40_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
    jar
    0.44
    Rig
    0.41
    sur
    0.41
     graciously
    0.39
     quadri
    0.38
     Rig
    0.38
    ee
    0.38
    カ
    0.38
    wig
    0.37
    squared
    0.37
    POSITIVE LOGITS
     interleaved
    0.43
    শ্ব
    0.41
    તો
    0.40
    祟
    0.40
    𒈬
    0.39
    叶
    0.39
    苇
    0.39
     daran
    0.38
    ابعه
    0.38
    ಾಗಿತ್ತು
    0.38
    Activations Density 0.000%

    No Known Activations