© 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. 2008
    Prev
    Next
    INDEX
    Explanations

    Database reader and code components

    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
    ولد
    0.40
    ennzeichnet
    0.40
    atenated
    0.38
    ittäin
    0.38
     }}=
    0.37
    detailID
    0.36
    structed
    0.36
     taped
    0.35
    antiated
    0.35
    groupID
    0.35
    POSITIVE LOGITS
    Source
    0.37
    cloud
    0.37
    shadow
    0.34
     Transcription
    0.34
    Cloud
    0.34
    ⁹
    0.34
    src
    0.33
     mic
    0.33
     života
    0.32
     स्रोत
    0.32
    Activations Density 0.049%

    No Known Activations