© 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. 56387
    Prev
    Next
    INDEX
    Explanations

    character descriptions and roles

    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
    Rubber
    0.47
    rubber
    0.44
     rubber
    0.43
    Cup
    0.40
    К
    0.40
    Wonder
    0.40
     телефон
    0.39
    rika
    0.39
    dome
    0.39
     rubbers
    0.38
    POSITIVE LOGITS
     Haj
    0.41
     operativa
    0.40
     ssid
    0.39
     recording
    0.39
    [(
    0.39
     ofx
    0.38
    ',(
    0.38
    宍
    0.38
     soaking
    0.38
     permitting
    0.37
    Activations Density 0.007%

    No Known Activations