© 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. 224842
    Prev
    Next
    INDEX
    Explanations

    commercially, aware, hands, handle it

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

    firm or extra-firm

    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
     prí
    0.46
     empowered
    0.44
     จุด
    0.44
     be
    0.44
     Columbia
    0.44
     IE
    0.44
    åg
    0.43
     Ð
    0.43
     ตำ
    0.43
     ré
    0.43
    POSITIVE LOGITS
     ساری
    0.49
    作战
    0.49
     environs
    0.48
    런
    0.48
    衬
    0.46
    逦
    0.46
    Vari
    0.45
    Aryan
    0.44
    вары
    0.44
     જય
    0.44
    Activations Density 0.001%

    No Known Activations