© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138293
    Prev
    Next
    INDEX
    Explanations

    collocational features

    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_16_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
     standalone
    0.49
     tangent
    0.48
     revitalization
    0.48
     stable
    0.47
     Shrewsbury
    0.46
     run
    0.46
    )`
    0.46
    boolProp
    0.46
     destabil
    0.46
     standard
    0.46
    POSITIVE LOGITS
    ন
    0.59
    ન
    0.57
    न
    0.55
     électriques
    0.55
    n
    0.55
     elektry
    0.54
    א
    0.54
    н
    0.53
    ن
    0.53
     elektron
    0.53
    Activations Density 0.000%

    No Known Activations