© 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. 144079
    Prev
    Next
    INDEX
    Explanations

    Key followed by a colon or explanation

    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
    いち
    0.54
     উদ্বাস্তু
    0.49
    ным
    0.46
     minimized
    0.46
    ਉਣ
    0.46
    ତି
    0.44
    ଝ
    0.44
     उठाया
    0.43
    getFullName
    0.43
    ᱛ
    0.43
    POSITIVE LOGITS
     Lew
    0.51
     jaunes
    0.50
     Opp
    0.48
     Quelles
    0.48
     masc
    0.47
     Dort
    0.45
     scheming
    0.45
     Mari
    0.43
     Spartan
    0.43
     vess
    0.43
    Activations Density 0.006%

    No Known Activations