© 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. 234852
    Prev
    Next
    INDEX
    Explanations

    states, accommodations, reward, feel

    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
    ere
    0.49
    ard
    0.44
     Backward
    0.44
     I
    0.44
    dehyde
    0.44
    ences
    0.43
    k
    0.42
     G
    0.41
    lom
    0.41
     calor
    0.41
    POSITIVE LOGITS
    貶
    0.50
    Void
    0.49
    ল
    0.48
    бва
    0.48
    必須
    0.48
    贬
    0.48
     होंगी
    0.47
    ன்
    0.47
    items
    0.47
    詼
    0.47
    Activations Density 0.001%

    No Known Activations