© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3172
    Prev
    Next
    INDEX
    Explanations

    dependencies, licenses, specialty type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    ICE
    1.49
    ice
    1.48
     gray
    1.42
    6
    1.35
    Categorie
    1.34
    ICES
    1.34
    Entities
    1.32
    Collection
    1.31
     finito
    1.27
    recognizable
    1.27
    POSITIVE LOGITS
     dysplasia
    1.36
     troubleshoot
    1.31
    Cllr
    1.26
    auan
    1.24
    購
    1.23
    unky
    1.23
    müşt
    1.23
    鬚
    1.23
    ointees
    1.22
    夫妇
    1.21
    Activations Density 0.016%

    No Known Activations