© 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. 61669
    Prev
    Next
    INDEX
    Explanations

    time of day

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

    dictate which, object removal, learns a

    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
     intercal
    0.43
    ⸱
    0.42
     prog
    0.42
    కి
    0.39
    剛
    0.39
    ɵ
    0.39
    …
    0.38
    ᱠ
    0.38
     ख़
    0.38
    ними
    0.38
    POSITIVE LOGITS
    schule
    0.53
    tell
    0.46
    sama
    0.41
    saan
    0.41
    ietro
    0.39
    teller
    0.39
    deh
    0.39
    mine
    0.39
    罐
    0.39
    تے
    0.38
    Activations Density 0.000%

    No Known Activations