© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5904
    Prev
    Next
    INDEX
    Explanations

    left and right directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asaan
    1.61
    atica
    1.59
    atic
    1.55
     készült
    1.49
     Donde
    1.49
    咿
    1.49
    licenses
    1.47
     brok
    1.44
    鉴
    1.44
    based
    1.42
    POSITIVE LOGITS
     left
    3.33
     LEFT
    3.30
    left
    3.08
    Left
    2.99
     izquierda
    2.86
     direita
    2.78
     esquerda
    2.75
     kanan
    2.75
    LEFT
    2.73
     Left
    2.72
    Activations Density 0.361%

    No Known Activations