© 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. 243087
    Prev
    Next
    INDEX
    Explanations

    of drugs, thinking, scanner, authority

    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
     வண்ணம்
    0.52
    コレート
    0.49
     जवळपास
    0.49
     producido
    0.48
    ޫ
    0.48
    手に
    0.48
     আক্রম
    0.47
     calitate
    0.47
     предвари
    0.46
    வினை
    0.46
    POSITIVE LOGITS
    0.57
     AW
    0.47
     ，
    0.44
     转
    0.43
     STORIES
    0.43
    ，
    0.43
     SPIR
    0.42
     Approval
    0.42
     दिखता
    0.42
     与
    0.41
    Activations Density 0.000%

    No Known Activations