© 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. 37483
    Prev
    Next
    INDEX
    Explanations

    or carve, y, straight

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

    vector representations of data

    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
     distressed
    0.40
    ोलिक
    0.40
    ர்ச்சி
    0.39
    وك
    0.39
    <0xCF>
    0.38
    வச
    0.38
    advised
    0.38
    sourced
    0.38
    僭
    0.38
    addSprite
    0.37
    POSITIVE LOGITS
    വാദ
    0.49
     embedding
    0.46
     Textbook
    0.46
     สนาม
    0.46
     Embedding
    0.46
     株
    0.45
     Place
    0.44
     tvrd
    0.44
     sanitaria
    0.42
     metoda
    0.42
    Activations Density 0.000%

    No Known Activations