© 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. 193455
    Prev
    Next
    INDEX
    Explanations

    years of

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

    hobbies makes, Bierstadt, immutability

    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
     Casi
    0.48
     Special
    0.47
     Freeze
    0.46
    薷
    0.45
     What
    0.45
     Helen
    0.44
     BufferedWriter
    0.44
     Curso
    0.44
     Production
    0.44
     Tages
    0.44
    POSITIVE LOGITS
     possessions
    0.49
     shackles
    0.47
     touches
    0.46
     নেতাদের
    0.46
     servitude
    0.46
     grams
    0.46
     gmin
    0.45
     slavery
    0.45
    ^{'
    0.44
     светло
    0.44
    Activations Density 0.000%

    No Known Activations