© 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-262K
    7. 32934
    Prev
    Next
    INDEX
    Explanations

    password completion

    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_262k_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
     TRANSPORTURI
    0.50
    а
    0.49
    фи
    0.47
    ЛИ
    0.43
    о
    0.42
    ר
    0.42
    е
    0.42
    importanza
    0.42
    ш
    0.42
    ich
    0.42
    POSITIVE LOGITS
     outside
    0.38
     exterior
    0.36
     intestines
    0.35
     tracks
    0.35
     de
    0.34
     detour
    0.34
     container
    0.33
     luar
    0.33
     membranes
    0.33
     superimposed
    0.33
    Activations Density 0.293%

    No Known Activations