© 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. 191454
    Prev
    Next
    INDEX
    Explanations

    honest day stuff Hungarian string

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

    explicitly stated goals

    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
    這一
    0.52
    こうした
    0.48
    ]>
    0.46
    こちらの
    0.46
    全世界
    0.46
    この
    0.45
    这一
    0.45
    ванне
    0.45
    這
    0.45
    冊
    0.45
    POSITIVE LOGITS
    ités
    0.52
     of
    0.49
    č
    0.47
     autrefois
    0.47
     allied
    0.45
     sõ
    0.45
     ʻ
    0.45
     Võ
    0.44
     perched
    0.42
    eram
    0.42
    Activations Density 0.000%

    No Known Activations