© 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. 4373
    Prev
    Next
    INDEX
    Explanations

    concepts and information

    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
    1
    1.09
    9
    1.08
    5
    1.01
    7
    0.97
    0
    0.95
    rinsic
    0.95
     silah
    0.92
     makeSound
    0.89
    ινων
    0.88
     Professions
    0.87
    POSITIVE LOGITS
    assie
    1.34
    acle
    1.32
    ザ
    1.30
    シー
    1.27
     overcome
    1.26
     overcomes
    1.25
     eels
    1.25
    tle
    1.25
     leukaemia
    1.23
     Heidelberg
    1.23
    Activations Density 0.052%

    No Known Activations