© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 122318
    Prev
    Next
    INDEX
    Explanations

    weekend bargain

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

    language, symbols, and specific terms

    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
     appliqu
    0.50
    ,
    0.50
    œ
    0.48
    4
    0.48
     are
    0.47
     will
    0.47
    ostic
    0.47
     wannan
    0.47
    ”
    0.46
     /
    0.46
    POSITIVE LOGITS
     वीक
    0.46
     தம்
    0.44
     जून
    0.44
     मानसून
    0.44
    境外
    0.44
     ಬಂಧ
    0.44
     तापमान
    0.43
    தற்காக
    0.43
    اه
    0.42
    季
    0.42
    Activations Density 0.000%

    No Known Activations