© 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. 145054
    Prev
    Next
    INDEX
    Explanations

    various specific functions

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

    IBM, specific names, clients

    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
    新
    0.48
    business
    0.47
    の新
    0.46
    plans
    0.45
    loans
    0.45
    Công
    0.42
     Bank
    0.41
    员工
    0.41
    量
    0.41
    精准
    0.41
    POSITIVE LOGITS
     çeşitli
    0.51
     zahr
    0.48
     spielt
    0.48
     verschiedenen
    0.47
     normalerweise
    0.47
     hauptsächlich
    0.47
     prehistoric
    0.46
     funktion
    0.46
     develops
    0.45
     inescap
    0.45
    Activations Density 0.002%

    No Known Activations