© 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. 186447
    Prev
    Next
    INDEX
    Explanations

    only identify

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

    ownership and replacement 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
     wasnt
    0.47
    器的
    0.44
     errors
    0.43
     primary
    0.42
     horrend
    0.42
     Terminator
    0.42
    );
    0.41
     damal
    0.40
    |
    0.40
     hatte
    0.39
    POSITIVE LOGITS
     자동차
    0.55
     автомоби
    0.51
    자동차
    0.49
    やお
    0.49
    荪
    0.49
    酺
    0.48
    inizin
    0.48
    inqui
    0.47
    ਲ
    0.47
    волю
    0.46
    Activations Density 0.000%

    No Known Activations