© 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. 156967
    Prev
    Next
    INDEX
    Explanations

    shoot, shooting, risk

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

    prepositional phrases indicating action

    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
     invoicing
    0.52
     `>=`,
    0.45
     przen
    0.45
    AZIONE
    0.45
     सरकारों
    0.45
    ATES
    0.44
     nationwide
    0.44
     continueRoutine
    0.44
    હિતી
    0.44
    ங்களிலும்
    0.44
    POSITIVE LOGITS
     I
    0.49
    人気
    0.46
    ↵↵
    0.46
        
    0.44
     fata
    0.43
    *,
    0.43
     Long
    0.42
    สำหรับ
    0.41
     длина
    0.41
     Ive
    0.40
    Activations Density 0.001%

    No Known Activations