© 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. 163068
    Prev
    Next
    INDEX
    Explanations

    specific actions or outcomes

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

    expand, elaboration, lists

    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
     іх
    0.45
     ሙ
    0.44
     മോ
    0.44
     tutte
    0.43
    inspection
    0.43
     останов
    0.42
     переста
    0.41
     сад
    0.41
     всіх
    0.41
     ቲ
    0.41
    POSITIVE LOGITS
     Flushing
    0.51
     Figur
    0.50
    u
    0.50
    बद्दल
    0.47
     EMEA
    0.47
     Obj
    0.46
    AA
    0.46
    MenuGroup
    0.46
     Debi
    0.46
     Prabhu
    0.46
    Activations Density 0.000%

    No Known Activations