© 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. 13897
    Prev
    Next
    INDEX
    Explanations

    disturbs the, Nell lay

    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
    屑
    0.56
    ㈠
    0.55
    りたい
    0.48
    supportsFocus
    0.46
    <0x8D>
    0.46
    排放
    0.45
    ısıyla
    0.45
    咭
    0.44
     વાંચો
    0.43
    ाइन
    0.43
    POSITIVE LOGITS
     Rip
    0.45
    မြ
    0.43
     are
    0.43
     at
    0.42
    ക്കുന്ന
    0.42
     hyperfine
    0.42
    പ്പിക്കുന്ന
    0.41
     Ripley
    0.41
     anonymously
    0.41
     pallets
    0.41
    Activations Density 0.000%

    No Known Activations