© 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. 195554
    Prev
    Next
    INDEX
    Explanations

    depreciating value

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

    R code

    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
     తాను
    0.50
    全面的
    0.44
     అన్ని
    0.44
    퉁
    0.43
    NgramModel
    0.42
     multiplies
    0.42
     एनिमल
    0.42
    每一
    0.42
     empowered
    0.42
     అవు
    0.41
    POSITIVE LOGITS
    mortem
    0.50
     Knob
    0.49
     puc
    0.49
    findings
    0.49
    rendering
    0.48
    putar
    0.47
    ान्स
    0.47
    t
    0.46
    alog
    0.46
    tura
    0.46
    Activations Density 0.001%

    No Known Activations