© 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-262K
    7. 25558
    Prev
    Next
    INDEX
    Explanations

    say if

    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_262k_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
    若
    0.53
    箭
    0.47
    น
    0.46
    }$,
    0.46
    โรค
    0.45
     bacterium
    0.45
    로
    0.45
    ณี
    0.45
    ，
    0.44
    how
    0.44
    POSITIVE LOGITS
     Prussian
    0.52
     Hölder
    0.52
     Québec
    0.52
     Untersuchung
    0.51
     Printing
    0.47
     Maintenance
    0.47
     Places
    0.46
     Loth
    0.46
     Auff
    0.46
     Böl
    0.46
    Activations Density 0.005%

    No Known Activations