© 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. 48754
    Prev
    Next
    INDEX
    Explanations

    patent license grants

    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
    dinger
    0.46
    ية
    0.45
    pair
    0.44
    bling
    0.44
    ̉
    0.44
    adrat
    0.43
    čaj
    0.43
    书
    0.42
    at
    0.42
    fil
    0.41
    POSITIVE LOGITS
     keamanan
    0.48
     Brows
    0.45
     आए
    0.45
     अन्याय
    0.45
     makin
    0.44
    نتی
    0.44
     Irons
    0.44
     endonuclease
    0.44
    स्की
    0.44
     radiolysis
    0.44
    Activations Density 0.001%

    No Known Activations