© 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. 146345
    Prev
    Next
    INDEX
    Explanations

    Marathon Champ

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

    reporting and comprehensive details

    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
    ArchivePath
    0.48
    Publications
    0.47
    〔
    0.46
    rmsg
    0.46
    могою
    0.45
    Invalid
    0.44
     정부
    0.44
     fréquemment
    0.43
    рифт
    0.43
    ༸
    0.43
    POSITIVE LOGITS
     Bahamas
    0.50
    ichel
    0.48
     nello
    0.48
     NG
    0.47
     K
    0.47
     N
    0.47
     neither
    0.46
     multiply
    0.45
     Mediterranean
    0.45
     removal
    0.44
    Activations Density 0.001%

    No Known Activations