© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1646
    Prev
    Next
    INDEX
    Explanations

    context, purpose, tone, audience

    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_22_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
    ↵↵
    1.33
    ↵↵↵
    1.02
    ↵↵↵↵
    0.89
    ↵↵↵↵↵
    0.79
     Factors
    0.76
     Theories
    0.71
     Without
    0.68
    <start_of_image>
    0.68
     fattori
    0.68
     دون
    0.67
    POSITIVE LOGITS
    /
    0.84
     primarily
    0.82
     основном
    0.74
     envisage
    0.73
     mainly
    0.72
     exactamente
    0.71
    :**
    0.70
     approximately
    0.70
     envisaged
    0.69
     audience
    0.67
    Activations Density 0.506%

    No Known Activations