© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55610
    Prev
    Next
    INDEX
    Explanations

    customizing apps without modifying

    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_31_width_65k_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
    頬
    0.46
    lée
    0.46
    jahtera
    0.45
    rač
    0.44
     मात
    0.44
    एम
    0.44
    और
    0.43
    ющая
    0.43
     утро
    0.43
     ऋ
    0.43
    POSITIVE LOGITS
     window
    0.49
     detach
    0.48
    ocultural
    0.48
     perfor
    0.42
     حدود
    0.42
     defini
    0.42
    tod
    0.42
    habilit
    0.41
     components
    0.41
    話を
    0.41
    Activations Density 0.006%

    No Known Activations