© 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. 98363
    Prev
    Next
    INDEX
    Explanations

    endorsed , affiliated , or convenience

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

    medium variant, Markov property

    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
    즈
    0.46
    หรือ
    0.45
    *****",
    0.44
     activists
    0.43
    (`/
    0.43
    흐
    0.43
    或者
    0.43
    ="../../
    0.42
    行的
    0.41
     또는
    0.41
    POSITIVE LOGITS
    ار
    0.56
    fi
    0.55
     меч
    0.51
     ocasi
    0.50
     À
    0.49
    corrected
    0.49
     HRM
    0.48
     Richter
    0.48
     доказа
    0.48
     khẳng
    0.48
    Activations Density 0.001%

    No Known Activations