© 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. 121629
    Prev
    Next
    INDEX
    Explanations

    dreams to vision working critical edition developer driver

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

    Write your

    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
     eBooks
    0.49
     tasas
    0.47
    𝙼
    0.46
     Embed
    0.46
     pront
    0.46
     leyes
    0.46
     litres
    0.45
     lw
    0.45
     Eps
    0.45
     Preset
    0.45
    POSITIVE LOGITS
    trans
    0.54
    att
    0.53
     陳
    0.52
    臟
    0.51
    atal
    0.51
    indian
    0.51
    0
    0.50
    ائها
    0.48
    3
    0.48
    clustering
    0.48
    Activations Density 0.000%

    No Known Activations