© 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. 204156
    Prev
    Next
    INDEX
    Explanations

    dealing with

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

    GPT-4 Turbo

    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
    }$
    0.43
    했다
    0.43
    zona
    0.43
     said
    0.42
    ας
    0.42
     seemingly
    0.41
    artig
    0.41
     så
    0.41
     blok
    0.40
    }\}$
    0.39
    POSITIVE LOGITS
     ہوسک
    0.47
    改變
    0.46
    蛲
    0.44
     แปร
    0.44
     تحليل
    0.44
     análisis
    0.43
    转变
    0.43
    ால
    0.42
     Analy
    0.41
    면에
    0.39
    Activations Density 0.001%

    No Known Activations