© 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. 44706
    Prev
    Next
    INDEX
    Explanations

    hybrid cable, Outlook, Harman brand

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

    specific contexts or descriptions

    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
    SPs
    0.51
    RP
    0.50
    LD
    0.49
    z
    0.48
    Ｒ
    0.48
    】
    0.46
    》。
    0.46
    R
    0.45
    】-
    0.45
     tén
    0.44
    POSITIVE LOGITS
     frío
    0.49
     fiind
    0.47
    까지
    0.46
    未來
    0.46
     вернуться
    0.46
     almacenar
    0.46
    ერს
    0.45
     unwarrant
    0.45
     frio
    0.45
     अनावश्यक
    0.44
    Activations Density 0.000%

    No Known Activations