© 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. 61567
    Prev
    Next
    INDEX
    Explanations

    Valentine's Day card, hechsher, irregular verbs, feedback, curry

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

    to despair

    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
    w
    0.46
    usr
    0.45
    Tere
    0.44
    DO
    0.43
     endeavor
    0.43
    the
    0.42
    inch
    0.41
     husbandry
    0.41
    umbra
    0.40
    admin
    0.40
    POSITIVE LOGITS
     숫
    0.55
     शहरा
    0.49
     数
    0.48
     숫자
    0.48
     peça
    0.47
    碣
    0.46
    可以说
    0.46
    汨
    0.46
     boils
    0.46
     lepší
    0.46
    Activations Density 0.000%

    No Known Activations