© 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. 155963
    Prev
    Next
    INDEX
    Explanations

    often ways, steal them

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

    pattern definition or code snippet

    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
     ক্ষতি
    0.49
    뼈
    0.48
     tarses
    0.48
    ാള
    0.47
     rzeczyw
    0.46
    륵
    0.46
    ፍ
    0.45
    桎
    0.45
    他不
    0.44
    krank
    0.44
    POSITIVE LOGITS
    TE
    0.49
    ampton
    0.48
     enriched
    0.48
    entingan
    0.47
    encore
    0.46
     করলেন
    0.46
    ocious
    0.46
    en
    0.46
    end
    0.46
     heated
    0.46
    Activations Density 0.000%

    No Known Activations