© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1604
    Prev
    Next
    INDEX
    Explanations

    creative content formats

    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
    licos
    0.33
    нали
    0.31
    ची
    0.31
    龴
    0.30
    obviously
    0.30
     стати
    0.30
     असून
    0.30
    ংস
    0.29
    শনার
    0.29
    intă
    0.29
    POSITIVE LOGITS
    ).
    0.33
    0.33
    ↵↵
    0.33
     Dataset
    0.31
    。
    0.30
     Pilot
    0.29
     Fabric
    0.29
    ].
    0.29
     No
    0.28
     Realm
    0.28
    Activations Density 0.221%

    No Known Activations