© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 286
    Prev
    Next
    INDEX
    Explanations

    least used words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     nombreux
    2.57
     fréquentes
    2.44
     ofta
    2.42
    常常
    2.35
    鳅
    2.30
     selalu
    2.30
     nombreuses
    2.23
     always
    2.20
     czasem
    2.19
     both
    2.18
    POSITIVE LOGITS
    icin
    2.77
     Intents
    2.72
    rinsic
    2.68
     monomers
    2.58
    ograft
    2.56
    7
    2.54
    typen
    2.54
    otrop
    2.54
    <unused505>
    2.53
    Entities
    2.51
    Activations Density 0.098%

    No Known Activations