© 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. 145767
    Prev
    Next
    INDEX
    Explanations

    offers and deals

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

    claims, theories, results

    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
    অর্থাৎ
    0.49
     científica
    0.44
     scept
    0.43
     repel
    0.43
     skeptical
    0.43
    ミ
    0.43
    ញ្
    0.43
     scientifically
    0.43
    သည်။
    0.43
    Pager
    0.42
    POSITIVE LOGITS
     Anmeldung
    0.59
     langue
    0.55
    <0x80>
    0.48
     alcuni
    0.47
    izmus
    0.47
     Vereinig
    0.45
     Some
    0.45
     anmelden
    0.44
     acesso
    0.44
     Erectile
    0.44
    Activations Density 0.000%

    No Known Activations