© 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. 110204
    Prev
    Next
    INDEX
    Explanations

    surcharge per, processing plant, crashed shortly, COMPLEMENT

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

    required for, x, Independence

    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
    hares
    0.46
     THERE
    0.45
    THERE
    0.44
    niv
    0.43
    naj
    0.42
    akum
    0.42
    W
    0.42
    chool
    0.41
    reven
    0.41
    naye
    0.40
    POSITIVE LOGITS
     tokenizer
    0.49
     elucidation
    0.46
     dispersing
    0.46
     extractor
    0.42
     beak
    0.42
     retardation
    0.42
     chatted
    0.42
    醂
    0.42
    انہ
    0.41
     renderer
    0.41
    Activations Density 0.002%

    No Known Activations