© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 136225
    Prev
    Next
    INDEX
    Explanations

    directional terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     жили
    0.46
    }$&$
    0.44
    เจ้า
    0.42
     ১৫০
    0.39
    ::$
    0.38
     রঙ্গ
    0.38
    FILE
    0.38
    ullo
    0.38
    洽
    0.37
     жил
    0.37
    POSITIVE LOGITS
    Vertical
    0.43
     directional
    0.42
    色列
    0.39
     horizontal
    0.39
     Vertical
    0.39
     vertical
    0.38
    DebugSymbols
    0.37
    étricas
    0.36
    とめ
    0.36
    directional
    0.36
    Activations Density 0.000%

    No Known Activations