© 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. 51475
    Prev
    Next
    INDEX
    Explanations

    project years

    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
    ளையும்
    0.45
    फु
    0.43
    叄
    0.43
    鏨
    0.43
    పడుతుంది
    0.43
    ቀም
    0.42
    ཋ
    0.42
    ടുത
    0.42
     lapisan
    0.41
     spineItem
    0.41
    POSITIVE LOGITS
     ήταν
    0.44
    X
    0.44
    W
    0.41
     Years
    0.39
    T
    0.39
    _
    0.39
     (
    0.38
    '(
    0.38
     داشت
    0.38
    ayaran
    0.38
    Activations Density 0.029%

    No Known Activations