© 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. 64577
    Prev
    Next
    INDEX
    Explanations

    describing or discussing

    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
     Sacred
    0.43
    State
    0.43
     State
    0.43
    ");
    0.41
     Context
    0.41
    ").
    0.40
     States
    0.40
     Prevalence
    0.40
    )(
    0.39
    .",
    0.39
    POSITIVE LOGITS
     perdagangan
    0.47
     և
    0.46
     économique
    0.46
     площа
    0.44
     pembayaran
    0.44
     shipyard
    0.43
     maturities
    0.43
    ヴォ
    0.42
     expropri
    0.42
     inhomogeneous
    0.42
    Activations Density 0.015%

    No Known Activations