© 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. 20242
    Prev
    Next
    INDEX
    Explanations

    levels, density, volubility

    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
    muted
    0.45
    хий
    0.43
    \
    0.42
     الرجال
    0.42
    𝐝
    0.42
    \)
    0.41
    ),]
    0.41
    \}$
    0.41
    др
    0.41
    Annotations
    0.41
    POSITIVE LOGITS
     iyong
    0.51
     bertanggung
    0.49
     Roberto
    0.47
     synerg
    0.47
     Seite
    0.45
    ToMany
    0.45
     pracę
    0.45
     kerja
    0.45
     Dengan
    0.44
     Muito
    0.44
    Activations Density 0.011%

    No Known Activations