© 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. 29163
    Prev
    Next
    INDEX
    Explanations

    any other

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

    it made

    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
    ियम
    0.43
     lô
    0.42
     enthal
    0.42
     complic
    0.41
     využ
    0.41
     vài
    0.41
     coax
    0.41
     ὑ
    0.40
     lobes
    0.40
     harnesses
    0.40
    POSITIVE LOGITS
    foods
    0.47
    localisation
    0.45
    plaats
    0.45
    none
    0.44
    state
    0.43
    cc
    0.43
    nek
    0.43
    ik
    0.43
    plasma
    0.43
    addr
    0.42
    Activations Density 0.000%

    No Known Activations