© 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. 169860
    Prev
    Next
    INDEX
    Explanations

    exploring topics responsibly

    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
     COMPOUNDS
    0.49
     HALL
    0.45
    ขณะ
    0.45
    ૬
    0.44
    РО
    0.42
    HALL
    0.42
    ᒫ
    0.42
     STATE
    0.40
    は何
    0.40
    ៥
    0.40
    POSITIVE LOGITS
     die
    0.56
    er
    0.52
     Salomon
    0.50
     rarely
    0.48
    ophiles
    0.47
     to
    0.47
     izinsuku
    0.46
     que
    0.45
    ješt
    0.45
     that
    0.45
    Activations Density 0.003%

    No Known Activations