© 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. 46728
    Prev
    Next
    INDEX
    Explanations

    sworn to, cutest little, heading off

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

    proposed and consultant topics

    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
    omone
    0.48
     ecosystem
    0.46
     최대한
    0.46
    ite
    0.45
     activations
    0.45
    <\/
    0.45
    Place
    0.44
     चे
    0.44
    kev
    0.43
     robotic
    0.43
    POSITIVE LOGITS
     proposto
    0.48
    ပို့
    0.46
     Theoretically
    0.43
    詷
    0.43
    ルダー
    0.43
    মতো
    0.42
    цима
    0.42
     അരി
    0.42
    的故事
    0.41
    щиков
    0.41
    Activations Density 0.000%

    No Known Activations