© 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. 79995
    Prev
    Next
    INDEX
    Explanations

    dating profile

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

    sometimes and adjustments

    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
    ري
    0.43
    ubuk
    0.43
    쩝
    0.43
    зит
    0.42
    ktrum
    0.42
    ѫ
    0.42
    PERMISSION
    0.41
    만
    0.41
    عبة
    0.41
    ৪৩
    0.41
    POSITIVE LOGITS
     असले
    0.52
     emphasize
    0.49
     continue
    0.48
     comorbidities
    0.47
     corresponding
    0.47
     stipulated
    0.47
     التي
    0.46
     KE
    0.46
     priming
    0.46
     ውጤ
    0.46
    Activations Density 0.000%

    No Known Activations