© 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. 40-GEMMASCOPE-2-RES-65K
    7. 55206
    Prev
    Next
    INDEX
    Explanations

    webpage titles

    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_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
     META
    0.45
     विरो
    0.43
    META
    0.43
    𒈨
    0.42
     metastasis
    0.42
    𐰣
    0.42
     مرة
    0.41
    🦳
    0.41
    徬
    0.41
    怵
    0.40
    POSITIVE LOGITS
    kin
    0.41
    eno
    0.40
    ul
    0.39
    friend
    0.39
    fa
    0.39
    OD
    0.38
    imum
    0.38
    ego
    0.38
    ky
    0.38
    kill
    0.38
    Activations Density 0.009%

    No Known Activations