© 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. 56753
    Prev
    Next
    INDEX
    Explanations

    date, existence, commerce, detailed

    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
     gluing
    0.46
     normalerweise
    0.46
     ordinairement
    0.43
    匁
    0.43
     nehmen
    0.42
     meestal
    0.42
    foils
    0.41
    izontal
    0.41
     habituellement
    0.41
    gateTime
    0.40
    POSITIVE LOGITS
    2
    0.50
    3
    0.43
    Resolve
    0.42
    意
    0.42
    ]=
    0.41
    куда
    0.41
     உறுதி
    0.41
    Entity
    0.40
     of
    0.40
     Vanguard
    0.40
    Activations Density 0.002%

    No Known Activations