© 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. 49164
    Prev
    Next
    INDEX
    Explanations

    portable wet

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

    beginning / initial stages

    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
     erud
    0.47
     ఎలా
    0.46
    shah
    0.46
     പിന്നീട്
    0.44
    鏉
    0.43
    こそ
    0.43
    餬
    0.43
    ሒ
    0.43
    ილი
    0.42
    ůj
    0.41
    POSITIVE LOGITS
    মাত্র
    0.44
     inicialmente
    0.44
    甸
    0.43
    adium
    0.43
     promote
    0.42
    promoting
    0.42
     geen
    0.41
    promote
    0.41
     initially
    0.41
     ngừng
    0.41
    Activations Density 0.000%

    No Known Activations