© 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. 40775
    Prev
    Next
    INDEX
    Explanations

    repeat or renew actions

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

    follow-up questions and variations

    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
     Myst
    0.46
     perfil
    0.41
    <0x80>
    0.40
    Myst
    0.40
     abstra
    0.40
     desapare
    0.39
     vorge
    0.39
     manifi
    0.39
     emplacement
    0.39
    ренных
    0.39
    POSITIVE LOGITS
    🔁
    0.54
     substitutions
    0.52
     SECOND
    0.51
     reusing
    0.51
     recalcul
    0.51
    機制
    0.50
    🔄
    0.50
     recirculation
    0.48
     Option
    0.46
     reuse
    0.46
    Activations Density 0.102%

    No Known Activations