© 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. 242906
    Prev
    Next
    INDEX
    Explanations

    destroy the, demolish their, sentenced to

    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
    বহ
    0.52
    Expanding
    0.52
     adversity
    0.47
    ഡ്
    0.46
    Spr
    0.46
    хід
    0.46
    ACY
    0.45
    น
    0.45
    ൬
    0.45
    Parad
    0.44
    POSITIVE LOGITS
    alagi
    0.46
     Neues
    0.45
    atzeko
    0.45
     ></
    0.45
     <>
    0.44
    ar
    0.43
    inelli
    0.43
    id
    0.43
    brevi
    0.42
    raltar
    0.42
    Activations Density 0.000%

    No Known Activations