© 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. 19741
    Prev
    Next
    INDEX
    Explanations

    implementation cost

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

    numerical calculations and units

    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
    ，
    0.50
    、
    0.43
     রাখার
    0.40
    IED
    0.39
    eyen
    0.39
    以便
    0.37
    yenne
    0.36
     Ate
    0.36
    ،
    0.36
    款
    0.36
    POSITIVE LOGITS
     wai
    0.44
     squats
    0.43
     réseaux
    0.42
    alunos
    0.42
    MPs
    0.41
     summarised
    0.41
    Références
    0.41
     topography
    0.40
     პირ
    0.40
     ethernet
    0.40
    Activations Density 0.000%

    No Known Activations