© 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. 84124
    Prev
    Next
    INDEX
    Explanations

    foreign language or special tokens

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

    lacking completeness

    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
    خ
    0.52
     Territorial
    0.47
    ά
    0.47
     territory
    0.45
     Wire
    0.45
    <i>
    0.44
     χ
    0.44
    ὡ
    0.44
     puiss
    0.44
     Button
    0.43
    POSITIVE LOGITS
    }^{+}=
    0.57
    teilung
    0.51
     చేస్తున్నారు
    0.51
    uak
    0.50
    }^{+}
    0.50
    }^{*}(
    0.49
    nahmen
    0.49
    hada
    0.48
    tuvo
    0.48
     encontraron
    0.47
    Activations Density 0.000%

    No Known Activations