© 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. 132920
    Prev
    Next
    INDEX
    Explanations

    birds, Films, Go, blame, men, Board

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

    breakdown of sections and strategies

    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
     Roya
    0.45
    ccccc
    0.43
     distin
    0.42
    jati
    0.42
    ṛ
    0.42
     энергети
    0.41
     ocorreu
    0.41
     पुढील
    0.40
     Cambrian
    0.40
     habían
    0.40
    POSITIVE LOGITS
     godziny
    0.48
     postponed
    0.48
    疣
    0.47
     isn
    0.45
     manages
    0.44
     overclock
    0.44
     advertised
    0.43
     garg
    0.43
     এসব
    0.42
    า
    0.42
    Activations Density 0.000%

    No Known Activations