© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116810
    Prev
    Next
    INDEX
    Explanations

    consent withheld unreasonably

    np_acts-logits-general · gemini-2.5-flash-lite

    choosing after certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    فس
    0.43
    ']
    0.43
     維尼
    0.41
    هرة
    0.41
    </b>
    0.41
    vis
    0.41
     FSC
    0.40
    <unused60>
    0.40
     Cultural
    0.40
    fontSize
    0.40
    POSITIVE LOGITS
     AliExpress
    0.53
     outage
    0.50
     ウ
    0.50
     Marzo
    0.49
     overhaul
    0.48
    켠
    0.48
    온
    0.48
     ती
    0.47
    쫒
    0.47
     خرید
    0.46
    Activations Density 0.000%

    No Known Activations