© 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. 223319
    Prev
    Next
    INDEX
    Explanations

    Instagram influencer, to fire, old son

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

    quantitative, formal, fairness

    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
    ilación
    0.51
     Lúc
    0.50
     svo
    0.49
    ە
    0.49
     Kon
    0.49
    <0xE3>
    0.48
    complement
    0.48
     carv
    0.46
     Blast
    0.45
     Glove
    0.45
    POSITIVE LOGITS
    禺
    0.49
     validating
    0.47
    iph
    0.46
     зай
    0.46
     рей
    0.46
     validations
    0.46
    ти
    0.45
     серьез
    0.45
     गंभीर
    0.45
    ண்டும்
    0.45
    Activations Density 0.000%

    No Known Activations