© 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. 33814
    Prev
    Next
    INDEX
    Explanations

    neither nor

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

    GitHub repositories and releases

    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
     பார்க்கலாம்
    0.47
     मल्टी
    0.46
     வேல
    0.46
    トゥ
    0.45
     ediyoruz
    0.43
    ሸ
    0.43
     sıv
    0.42
     нашей
    0.42
    م
    0.42
    tevõ
    0.42
    POSITIVE LOGITS
     neither
    0.55
    neither
    0.48
     nominally
    0.47
     detained
    0.46
     politely
    0.45
     attendees
    0.44
     punishable
    0.44
     diverted
    0.44
     참석
    0.43
     officially
    0.43
    Activations Density 0.000%

    No Known Activations