© 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. 116354
    Prev
    Next
    INDEX
    Explanations

    specific word combinations

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

    names that evoke specific feelings

    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
    ாது
    0.50
    ax
    0.49
     delusions
    0.47
    den
    0.47
    an
    0.47
    lx
    0.46
    誰
    0.46
    fantasy
    0.46
    arag
    0.46
    axiom
    0.46
    POSITIVE LOGITS
     Emit
    0.52
     让
    0.49
    样品
    0.48
    )$.
    0.46
     Increase
    0.46
     augmente
    0.45
     ассорти
    0.45
     Alloy
    0.45
     EtOAc
    0.45
     emit
    0.44
    Activations Density 0.000%

    No Known Activations