© 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. 94998
    Prev
    Next
    INDEX
    Explanations

    website content discussion

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

    toxic atmosphere, presidential election, selectors

    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
     skeptical
    0.45
     frail
    0.44
     selfless
    0.44
    MathOperator
    0.42
     landfall
    0.42
    担
    0.42
    သည့်
    0.40
    的名
    0.39
     نحو
    0.39
     pending
    0.39
    POSITIVE LOGITS
    los
    0.52
    seau
    0.51
     geralmente
    0.50
    mss
    0.49
    siniz
    0.49
    parameters
    0.48
    mesa
    0.48
     Heir
    0.48
    𝙎
    0.47
    okok
    0.47
    Activations Density 0.000%

    No Known Activations