© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11895
    Prev
    Next
    INDEX
    Explanations

    code and math contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     harmless
    0.70
    紝
    0.67
    ...+
    0.67
     intentionally
    0.66
     "...
    0.65
    …,
    0.65
     Той
    0.63
    %',
    0.63
     bolts
    0.63
     subsidiaries
    0.62
    POSITIVE LOGITS
    financial
    0.84
    flu
    0.80
     Fisica
    0.80
    resp
    0.78
     thermique
    0.78
     prema
    0.77
     ditetapkan
    0.76
     Resmi
    0.76
    靴
    0.76
    oches
    0.75
    Activations Density 0.156%

    No Known Activations