© 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. 53941
    Prev
    Next
    INDEX
    Explanations

    registry is, audience ., Spirit to, liable for, market ., latest treatment, competitive advantages, institutional parties, lime juice

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

    technical and organizational terms

    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
    >"
    0.47
     জেনে
    0.46
    పంచ
    0.46
    સ્તુ
    0.45
    যন্ত্র
    0.44
     cpt
    0.44
    摄
    0.44
    texte
    0.44
     Meks
    0.44
    ilmesi
    0.43
    POSITIVE LOGITS
    থর
    0.47
     échantillons
    0.46
     Ramen
    0.45
    哧
    0.45
     diện
    0.45
     samples
    0.43
     listings
    0.43
     Einkauf
    0.42
     PP
    0.42
     Stores
    0.41
    Activations Density 0.000%

    No Known Activations