© 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. 14939
    Prev
    Next
    INDEX
    Explanations

    season is not

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

    with unseen or achievable

    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
    у
    0.49
    ера
    0.48
    ل
    0.46
    ería
    0.45
     තර
    0.44
    ᵉ
    0.43
    ĺ
    0.43
     प्रतिस्पर्
    0.43
    માં
    0.42
    Leer
    0.42
    POSITIVE LOGITS
    调度
    0.53
     heller
    0.48
     winkel
    0.46
     języ
    0.46
     مقام
    0.45
    <unused36>
    0.44
     电
    0.44
    仍
    0.43
    暴
    0.42
     seguito
    0.42
    Activations Density 0.000%

    No Known Activations