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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2864
    Prev
    Next
    INDEX
    Explanations

    code documentation summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    ҳо
    0.82
     stirring
    0.79
     spotlight
    0.75
     relief
    0.73
     …
    0.70
    ås
    0.70
     shutter
    0.69
     relieve
    0.69
     relieving
    0.67
     putting
    0.67
    POSITIVE LOGITS
     cref
    1.08
    inheritdoc
    1.00
    عبة
    0.90
    returns
    0.90
     क्वीन
    0.87
    Ƭ
    0.86
    Creates
    0.85
    remarks
    0.85
    Gets
    0.84
     BadRequest
    0.83
    Activations Density 0.008%

    No Known Activations