© 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. 136726
    Prev
    Next
    INDEX
    Explanations

    portable application, normal distribution, raise cholesterol

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

    description and examples

    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
     bew
    0.43
     glancing
    0.41
    噠
    0.41
    нова
    0.40
    RawContext
    0.40
    عة
    0.39
     utterance
    0.39
     vicinity
    0.39
    பெ
    0.38
    vaar
    0.38
    POSITIVE LOGITS
     수가
    0.48
    ĺ
    0.46
     দেয়
    0.45
    ltre
    0.45
    キャンペーン
    0.44
    就
    0.44
    리면
    0.44
    휠
    0.44
    št
    0.44
    smtb
    0.43
    Activations Density 0.000%

    No Known Activations