© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3318
    Prev
    Next
    INDEX
    Explanations

    most + qualifier

    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_16_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
    ك
    1.68
    는
    1.35
    ना
    1.27
    ()=>{
    1.25
    లను
    1.21
    ة
    1.17
    ির
    1.09
    ير
    1.09
    จะ
    1.06
    كار
    1.05
    POSITIVE LOGITS
    t
    2.19
    (
    1.40
    た
    1.29
    ד
    1.21
    T
    1.12
    of
    1.09
    S
    1.09
    tu
    1.07
    tive
    1.05
    tic
    1.04
    Activations Density 0.240%

    No Known Activations