© 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. 186649
    Prev
    Next
    INDEX
    Explanations

    Release, begun, decades

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

    haunting scaling difference offer documented

    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
    вах
    0.45
     المتح
    0.42
     extérieures
    0.40
    الب
    0.40
     GSi
    0.39
    羹
    0.39
    大赛
    0.39
    renched
    0.39
    睨
    0.38
    乎
    0.38
    POSITIVE LOGITS
    award
    0.57
    ed
    0.56
     begun
    0.53
    legisl
    0.53
    nd
    0.52
    .,
    0.52
     kidnap
    0.52
    ce
    0.51
    decade
    0.50
    render
    0.50
    Activations Density 0.000%

    No Known Activations