© 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. 193301
    Prev
    Next
    INDEX
    Explanations

    instructions, consulted, aged, corrected, authorized

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

    but frustration

    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
     foul
    0.55
    ↵
    0.54
    节
    0.52
     mudar
    0.50
    angar
    0.49
    ?
    0.49
     hormonal
    0.46
    Horizontal
    0.46
     TU
    0.46
     scald
    0.46
    POSITIVE LOGITS
    躹
    0.54
     क्विक
    0.53
    梩
    0.52
     वनस्प
    0.50
     चिल्ड्रन
    0.49
     полном
    0.49
    絓
    0.49
    ösung
    0.48
    olées
    0.48
    smöglichkeiten
    0.48
    Activations Density 0.000%

    No Known Activations