© 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. 72933
    Prev
    Next
    INDEX
    Explanations

    reading and believing

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

    explains conditional clauses

    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
    łaś
    0.49
     Pencil
    0.48
    feeding
    0.47
     (§
    0.47
     הן
    0.46
    ighth
    0.44
    “-
    0.44
    ม
    0.44
     arrondie
    0.44
     ENGINEERING
    0.44
    POSITIVE LOGITS
    怅
    0.44
    ત્રો
    0.43
    嬉しい
    0.43
     permiss
    0.42
    之际
    0.41
    魂
    0.41
    涅
    0.40
    大丈夫
    0.40
     విశ్వ
    0.40
    тернет
    0.39
    Activations Density 0.001%

    No Known Activations