© 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. 47764
    Prev
    Next
    INDEX
    Explanations

    existing pieces replaced ballroom

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

    introducing categories and key points

    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
     conductors
    0.43
     merchand
    0.43
     grids
    0.42
    дава
    0.41
    emote
    0.41
    ርስ
    0.40
     ~,
    0.39
     spare
    0.39
     ~
    0.38
     infer
    0.38
    POSITIVE LOGITS
    ENIDO
    0.46
     effettu
    0.44
    その後
    0.43
    亮相
    0.43
    இ
    0.42
    をはじめ
    0.42
    UpdateRequest
    0.41
    Ј
    0.41
    はじめ
    0.41
    PDF
    0.41
    Activations Density 0.000%

    No Known Activations