© 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. 7821
    Prev
    Next
    INDEX
    Explanations

    ozone layer, intentionally creating, used EVs

    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
    aplik
    0.38
    ๑
    0.35
    üler
    0.34
    ádio
    0.34
    अमेरिकी
    0.33
    ğ
    0.33
    א
    0.33
    ör
    0.32
    ischen
    0.32
    Altri
    0.32
    POSITIVE LOGITS
     AcOH
    0.31
     limitaciones
    0.31
     nettoy
    0.31
     limpeza
    0.31
     vésicules
    0.31
     clarinet
    0.30
     subgroups
    0.30
     Kxg
    0.30
     almeno
    0.29
     maximale
    0.29
    Activations Density 0.318%

    No Known Activations