© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166285
    Prev
    Next
    INDEX
    Explanations

    Terminal 0 Changing Value

    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_40_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
     Occupational
    0.42
     flourishes
    0.41
     Arabidopsis
    0.39
     acontecimientos
    0.38
    </h2>
    0.38
    Alliance
    0.38
    lot
    0.37
    </h3>
    0.37
     миро
    0.36
    aule
    0.36
    POSITIVE LOGITS
     disruptive
    0.40
     spare
    0.39
     rw
    0.39
     sole
    0.37
    identity
    0.37
     destructive
    0.37
     scan
    0.36
     nope
    0.36
     เงี้ย
    0.36
    rparam
    0.36
    Activations Density 0.000%

    No Known Activations