© 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. 161692
    Prev
    Next
    INDEX
    Explanations

    requirements or disposal

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

    statement or question structure

    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
    욜
    0.49
    άν
    0.49
     barrio
    0.47
    岨
    0.46
    บาด
    0.46
     angst
    0.46
    กระท
    0.45
     stalemate
    0.45
     thorax
    0.44
    گوید
    0.44
    POSITIVE LOGITS
    gré
    0.48
    ({\
    0.46
    ッド
    0.46
                    
    0.45
    purch
    0.44
    registers
    0.44
    +{\
    0.43
     villagers
    0.43
     تق
    0.42
    Brock
    0.42
    Activations Density 0.000%

    No Known Activations