© 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. 203250
    Prev
    Next
    INDEX
    Explanations

    numbers and sequences

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

    purpose and lifestyle

    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
     guessing
    0.47
    vh
    0.45
    ↵
    0.45
    .,
    0.45
    orden
    0.44
    yo
    0.44
    jk
    0.44
    ;
    0.44
    ce
    0.43
     meal
    0.43
    POSITIVE LOGITS
     επισ
    0.54
     Oke
    0.50
     gigantic
    0.46
     impressively
    0.45
     μία
    0.45
     భారీ
    0.45
    파일
    0.44
    そして
    0.44
     பாஜக
    0.43
     scripted
    0.43
    Activations Density 0.000%

    No Known Activations