© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3753
    Prev
    Next
    INDEX
    Explanations

    ftp, Dreams, API

    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
     Melo
    1.42
     scream
    1.36
     bangunan
    1.29
     Scream
    1.24
     Kohn
    1.20
     creazione
    1.17
    Somos
    1.16
    罷
    1.13
    ukun
    1.13
    imiya
    1.12
    POSITIVE LOGITS
     both
    1.32
     with
    1.26
     itinerary
    1.20
     on
    1.19
    bersome
    1.17
    V
    1.16
    President
    1.15
     shown
    1.14
    both
    1.11
     two
    1.11
    Activations Density 0.147%

    No Known Activations