© 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. 151107
    Prev
    Next
    INDEX
    Explanations

    expenses or heating

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

    achievement and pride

    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
     đất
    0.48
     Harlan
    0.46
     FREE
    0.44
    >>>
    0.44
     chiều
    0.44
     Ulu
    0.43
     Taman
    0.43
     taman
    0.41
     Zentrum
    0.41
    )^{*}
    0.40
    POSITIVE LOGITS
     poč
    0.46
    Statistical
    0.43
    ваць
    0.42
    पिछले
    0.42
    हीत
    0.42
    astung
    0.41
    gelt
    0.41
     humiliating
    0.40
    Achievement
    0.40
    зит
    0.40
    Activations Density 0.001%

    No Known Activations