© 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. 6055
    Prev
    Next
    INDEX
    Explanations

    fortify program

    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
     outcast
    0.26
     år
    0.26
     possibile
    0.26
    െല്ലാം
    0.25
    ಾ
    0.25
     avantaj
    0.25
    ים
    0.24
     অবস্থা
    0.24
     минут
    0.24
    െ
    0.24
    POSITIVE LOGITS
     Kentucky
    0.26
     Massachusetts
    0.24
    癌症
    0.24
     Katz
    0.24
     psychiatry
    0.24
     Colorado
    0.24
    helps
    0.24
    ingham
    0.23
    heart
    0.23
    ococcal
    0.23
    Activations Density 0.074%

    No Known Activations