© 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. 61541
    Prev
    Next
    INDEX
    Explanations

    of the

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

    creating or envisioning something

    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
    p
    0.54
    symmetry
    0.49
     متفاوت
    0.47
    eh
    0.46
    brushes
    0.46
    ochi
    0.46
    affine
    0.46
    membered
    0.45
     cakkh
    0.45
    铳
    0.45
    POSITIVE LOGITS
    Signup
    0.48
     Signup
    0.45
     Structure
    0.44
    ень
    0.43
     Webinar
    0.43
     ideally
    0.43
     Database
    0.43
     Surveillance
    0.43
    初回
    0.42
    ковник
    0.42
    Activations Density 0.000%

    No Known Activations