© 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. 158179
    Prev
    Next
    INDEX
    Explanations

    analysis or groups or stores

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

    data masking and reduction

    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
    に残
    0.47
     característica
    0.46
    鶴
    0.46
    搆
    0.46
    ლო
    0.45
    obacterial
    0.45
    Cruise
    0.45
    ᱴ
    0.45
    ಕೋ
    0.45
     الدي
    0.45
    POSITIVE LOGITS
     Vorsch
    0.53
     pegged
    0.49
    rename
    0.48
    nen
    0.48
     EventHandler
    0.47
    0
    0.47
     Loss
    0.47
    8
    0.46
    zhen
    0.46
    ]
    0.46
    Activations Density 0.000%

    No Known Activations