© 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. 155633
    Prev
    Next
    INDEX
    Explanations

    revising, training, decisions, rehearsing

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

    pre-marital counseling

    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
    ，
    0.53
     multiplicative
    0.51
     ，
    0.49
    件事情
    0.49
    ୃ
    0.46
    これが
    0.46
     crescita
    0.44
    喜
    0.44
     ،
    0.44
    clientes
    0.44
    POSITIVE LOGITS
    parsedBlock
    0.48
     flashed
    0.46
     Philosophical
    0.45
     appeared
    0.44
     Mauro
    0.43
     inny
    0.43
    సూ
    0.43
     Berlin
    0.43
     Philos
    0.42
    SpriteCollision
    0.42
    Activations Density 0.001%

    No Known Activations