© 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. 16929
    Prev
    Next
    INDEX
    Explanations

    specific goals for rephrasing

    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
    ph
    0.46
     उपकरण
    0.46
     问题
    0.46
     ਕਰੋ
    0.46
    ]++;
    0.45
    }^{-
    0.45
     тъ
    0.45
    য়ান
    0.45
    아
    0.45
     کۆ
    0.44
    POSITIVE LOGITS
     Sass
    0.44
     camaraderie
    0.44
     Tranqu
    0.42
     Batt
    0.42
     Spacious
    0.42
     despite
    0.41
     trotz
    0.41
     Boud
    0.41
     Bats
    0.41
     Rentals
    0.40
    Activations Density 0.006%

    No Known Activations