© 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. 218942
    Prev
    Next
    INDEX
    Explanations

    specific actions and entities

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

    fiber formation

    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
    son
    0.50
     Student
    0.44
     Transcription
    0.43
     Instructional
    0.43
     Traction
    0.42
    험
    0.42
     Witten
    0.41
    sson
    0.41
    el
    0.41
    umption
    0.40
    POSITIVE LOGITS
     licences
    0.51
    ༠
    0.51
     amacı
    0.51
     ofic
    0.50
     دوسروں
    0.48
     propias
    0.47
    JOR
    0.47
     fondée
    0.46
     critérios
    0.46
     oficinas
    0.46
    Activations Density 0.002%

    No Known Activations