© 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. 14418
    Prev
    Next
    INDEX
    Explanations

    not immediately, still

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

    TAM with ambition

    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
    커
    0.49
    ố
    0.48
    пере
    0.47
    י
    0.47
    rown
    0.46
    к
    0.46
    ạo
    0.46
    во
    0.43
    про
    0.43
    OT
    0.43
    POSITIVE LOGITS
     klimat
    0.54
     ماحول
    0.52
     heterocyclic
    0.50
     NPTypeCode
    0.50
     subjekt
    0.50
     anisotrop
    0.50
     surjective
    0.49
     adjuvant
    0.49
     stimul
    0.48
     priming
    0.48
    Activations Density 0.000%

    No Known Activations