© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22394
    Prev
    Next
    INDEX
    Explanations

    valid JSON

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ਕੀਤੀ
    0.39
    罣
    0.37
    พล
    0.36
    嚓
    0.36
     mehrerer
    0.36
    咖
    0.35
     društ
    0.35
     incó
    0.35
    )&=
    0.35
     раздра
    0.35
    POSITIVE LOGITS
     valid
    2.11
    valid
    1.84
    Valid
    1.72
     gült
    1.65
     Valid
    1.63
     válido
    1.48
     válida
    1.48
     VALID
    1.48
     valide
    1.45
    isValid
    1.38
    Activations Density 0.033%

    No Known Activations