© 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. 78278
    Prev
    Next
    INDEX
    Explanations

    excludes any

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

    vulnerability, halving, cog, system, headline, framework, longitude

    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
    t
    0.47
    partisan
    0.47
    કડ
    0.45
    ્યાં
    0.45
    स्पेक्टर
    0.45
    ਲ
    0.45
    庥
    0.44
    nombre
    0.44
    dfe
    0.43
    imal
    0.43
    POSITIVE LOGITS
     відповід
    0.54
     thrombo
    0.51
     мати
    0.49
    ти
    0.48
     rapproche
    0.47
     цю
    0.47
     믿
    0.46
     월
    0.45
     geeign
    0.45
     тариф
    0.45
    Activations Density 0.000%

    No Known Activations