© 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. 204938
    Prev
    Next
    INDEX
    Explanations

    mutant, fast, corner, unusual text

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

    asking about exploitation and rules

    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
    ილ
    0.48
    𝑙
    0.46
     bowel
    0.44
    नाव
    0.43
    मॉर्निंग
    0.43
     enlarge
    0.43
     eastward
    0.43
    ૈય
    0.42
    गो
    0.42
    睦
    0.42
    POSITIVE LOGITS
    spo
    0.47
     لأ
    0.45
    ويات
    0.45
     Prinzip
    0.45
     Azi
    0.44
    squared
    0.43
    adores
    0.42
     listings
    0.42
     prin
    0.41
    returned
    0.41
    Activations Density 0.000%

    No Known Activations