© 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. 3470
    Prev
    Next
    INDEX
    Explanations

    describes capabilities or attributes

    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
    氦
    0.79
    存在的
    0.75
    gas
    0.66
    mineral
    0.66
     Aron
    0.65
    HRIM
    0.65
    lair
    0.64
    POI
    0.63
    lares
    0.63
     exista
    0.62
    POSITIVE LOGITS
    PBS
    1.47
     뉴스
    1.47
    P
    1.44
    [.
    1.41
    εσ
    1.40
    |
    1.36
     Tiv
    1.34
    UC
    1.34
    Pho
    1.33
     Huntington
    1.33
    Activations Density 0.018%

    No Known Activations