© 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. 137050
    Prev
    Next
    INDEX
    Explanations

    synthetic black

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

    persuasively, State Victories, simple AI

    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
     Comprehensive
    0.50
     CLEAN
    0.45
     high
    0.43
     Epic
    0.43
     epic
    0.42
     mountain
    0.41
     +
    0.41
     worldwide
    0.40
     Cardiff
    0.40
     পর্বত
    0.40
    POSITIVE LOGITS
    Ignoring
    0.52
    inisc
    0.51
    omized
    0.48
    }:$
    0.48
    :");
    0.48
    lent
    0.48
    ”:
    0.47
    isely
    0.47
    est
    0.47
     solche
    0.47
    Activations Density 0.000%

    No Known Activations