© 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. 142279
    Prev
    Next
    INDEX
    Explanations

    Tuesday linkups

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

    `Box` `A` `For` `masculine` `consistently`

    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
    έρ
    0.59
    ก
    0.56
    ەکە
    0.51
    thermal
    0.50
    ୈ
    0.50
    ב
    0.49
     thermal
    0.49
    <0x0D>
    0.47
    анг
    0.46
    personalised
    0.45
    POSITIVE LOGITS
     لیے
    0.54
     Vars
    0.52
     docente
    0.52
     vara
    0.48
     Wochschr
    0.47
    ojas
    0.47
     akt
    0.47
     poes
    0.47
     acte
    0.47
     Contador
    0.46
    Activations Density 0.000%

    No Known Activations