© 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. 86099
    Prev
    Next
    INDEX
    Explanations

    singles and sets

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

    life and death concepts

    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
     Sánchez
    0.52
     Santos
    0.49
     Sanchez
    0.46
     présent
    0.46
    ضر
    0.45
     dynamical
    0.44
    桑
    0.41
     serata
    0.41
    港
    0.40
    浱
    0.40
    POSITIVE LOGITS
    /******/
    0.46
     ue
    0.46
     airing
    0.45
     cemeteries
    0.45
     aero
    0.45
     offence
    0.43
    Timestamp
    0.43
    AlignedText
    0.43
    Approach
    0.43
    itud
    0.43
    Activations Density 0.000%

    No Known Activations