© 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-65K
    7. 53038
    Prev
    Next
    INDEX
    Explanations

    full forms and descriptions

    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_65k_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
     нажа
    0.48
    Vol
    0.45
    Liquid
    0.43
     ва
    0.42
     тро
    0.42
    Fixed
    0.41
    华
    0.41
     пе
    0.40
    Marine
    0.40
     đàn
    0.40
    POSITIVE LOGITS
     generalizes
    0.50
     jeopard
    0.49
     amidst
    0.47
    পাড়া
    0.46
     allerlei
    0.46
    윕
    0.46
     jeopardize
    0.46
    لسط
    0.44
     einige
    0.44
     awhile
    0.44
    Activations Density 0.001%

    No Known Activations