© 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. 14585
    Prev
    Next
    INDEX
    Explanations

    calculation and verification

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

    modification, networks, complex models

    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
     může
    0.44
     permita
    0.42
     nincs
    0.42
     můžete
    0.40
     ikke
    0.40
    اهلا
    0.40
     दिखाता
    0.40
    襪
    0.39
     puedes
    0.39
     moż
    0.38
    POSITIVE LOGITS
     reformulation
    0.43
     calculation
    0.43
     reformulated
    0.43
     logistical
    0.41
    piry
    0.41
    twilio
    0.41
     commutation
    0.40
     rewrite
    0.40
     verification
    0.39
    MLE
    0.39
    Activations Density 0.000%

    No Known Activations