© 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. 209161
    Prev
    Next
    INDEX
    Explanations

    security deposit, balance account, they decide

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

    specific examples and technical terms

    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
     údaje
    0.46
    ？”
    0.45
    ⓧ
    0.44
    форд
    0.43
    刘
    0.43
     tohoto
    0.42
     Airtel
    0.42
     Avoid
    0.42
    ابعة
    0.42
     FMT
    0.42
    POSITIVE LOGITS
     ष
    0.50
    </b>
    0.50
     Νο
    0.49
     꿈
    0.49
     캠
    0.47
     چندین
    0.46
    Equation
    0.46
     शेख
    0.46
    anyak
    0.46
    plotting
    0.46
    Activations Density 0.001%

    No Known Activations