© 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-16K
    7. 11852
    Prev
    Next
    INDEX
    Explanations

    account currency

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

    variable name assignment or placeholder

    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_16k_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
    0.51
     which
    0.42
     any
    0.41
     olan
    0.40
     arit
    0.38
     stated
    0.38
     april
    0.37
     android
    0.36
     a
    0.36
     valued
    0.36
    POSITIVE LOGITS
    Bechyné
    0.48
    posure
    0.43
    🔦
    0.42
     సన్ని
    0.42
    sentation
    0.41
    ၡ
    0.41
    ⵥ
    0.41
    Méd
    0.41
    樑
    0.41
    殇
    0.41
    Activations Density 0.037%

    No Known Activations