© 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. 4725
    Prev
    Next
    INDEX
    Explanations

    yes or no contrast

    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
    WARD
    0.90
     aprendiz
    0.89
     palust
    0.82
    ourt
    0.80
    ildet
    0.78
     Verk
    0.78
    makt
    0.77
    梧
    0.76
    ward
    0.75
     fundraiser
    0.75
    POSITIVE LOGITS
    no
    2.74
    No
    2.73
     no
    2.68
     No
    2.65
     NO
    2.24
    NO
    2.01
    Yes
    2.00
     keine
    1.87
     none
    1.86
    yes
    1.82
    Activations Density 0.145%

    No Known Activations