© 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. 159177
    Prev
    Next
    INDEX
    Explanations

    preventable detentions, broken wing, weapon in

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

    sticky paws, acidification, copper tones, established, SpaceShip

    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
     ¥
    0.46
     Nhưng
    0.45
     でも
    0.45
    ￥
    0.45
     £
    0.44
     ګ
    0.43
    
    0.43
    ￡
    0.42
     例如
    0.41
     اكبر
    0.41
    POSITIVE LOGITS
    的环境
    0.52
    ചര്യ
    0.49
     environnement
    0.48
     síndrome
    0.46
    शंस
    0.46
    नव
    0.45
    秘书
    0.44
     dechlor
    0.44
     administratif
    0.44
     bindings
    0.43
    Activations Density 0.001%

    No Known Activations