© 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. 64565
    Prev
    Next
    INDEX
    Explanations

    granting permissions and rights

    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
     चुका
    0.45
     двор
    0.45
    疾患
    0.41
     whispered
    0.40
    ━━━━
    0.40
     flung
    0.38
     आजही
    0.36
    척
    0.36
     зи
    0.36
    ceptions
    0.36
    POSITIVE LOGITS
     dispensation
    0.46
     PURCH
    0.46
     request
    0.44
     downloading
    0.42
    ل
    0.40
     სტ
    0.40
    對於
    0.39
     purchaser
    0.39
    ാള
    0.39
    möglich
    0.39
    Activations Density 0.007%

    No Known Activations