© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 69879
    Prev
    Next
    INDEX
    Explanations

    my name is

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

    stating one's name

    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
     предназначен
    0.46
     the
    0.45
    环境下
    0.44
     eating
    0.44
     snacking
    0.43
     baking
    0.43
     acquiring
    0.42
    ॒
    0.42
     potting
    0.42
     removing
    0.42
    POSITIVE LOGITS
     말이
    0.55
     Είναι
    0.47
     არის
    0.46
    Lucida
    0.44
    ുകൊണ്ടാണ്
    0.44
    谲
    0.44
    Loren
    0.44
     sparkles
    0.43
    Origen
    0.43
    Leben
    0.42
    Activations Density 0.004%

    No Known Activations