© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 131955
    Prev
    Next
    INDEX
    Explanations

    until certain states or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tackling
    0.42
     gesprek
    0.42
     tackled
    0.40
    melidir
    0.40
    踊
    0.40
     messing
    0.39
    腼
    0.38
    事物
    0.38
     ouvr
    0.37
    動き
    0.37
    POSITIVE LOGITS
    isos
    0.36
     Godfrey
    0.36
     cattle
    0.36
    itivo
    0.36
     Bradshaw
    0.36
    ManagerState
    0.36
    िख
    0.35
    Alpine
    0.35
     mayoral
    0.35
    plus
    0.35
    Activations Density 0.001%

    No Known Activations