© 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. 232774
    Prev
    Next
    INDEX
    Explanations

    mountains and episodes

    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
    <0x86>
    0.47
     timed
    0.45
     Dock
    0.43
    кта
    0.43
     Bosnian
    0.40
     szí
    0.40
     Dorothe
    0.40
    ᅱ
    0.40
    рта
    0.39
    ك
    0.39
    POSITIVE LOGITS
    components
    0.50
     אך
    0.49
    år
    0.49
    LAGS
    0.47
     אם
    0.46
    𝐽
    0.46
    ctors
    0.46
    ပိုင်း
    0.46
    MOUNTAINS
    0.46
    DUCT
    0.46
    Activations Density 0.000%

    No Known Activations