© 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. 248609
    Prev
    Next
    INDEX
    Explanations

    developments and achievements

    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
    <unused41>
    0.55
    ３
    0.55
    误
    0.54
    thisStudent
    0.54
     ඔහු
    0.54
     स्पीकर
    0.53
    诈
    0.53
    跟踪
    0.52
     শুধ
    0.51
     presión
    0.50
    POSITIVE LOGITS
    0.54
     tom
    0.52
     methods
    0.45
     simplices
    0.45
    ]
    0.44
    ↵↵
    0.44
    .
    0.44
     developments
    0.43
    "
    0.43
     achievements
    0.42
    Activations Density 0.000%

    No Known Activations