© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1842
    Prev
    Next
    INDEX
    Explanations

    tried all or these

    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_16k_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
    itize
    1.92
    난다
    1.85
    orsch
    1.77
    powiedz
    1.73
    ουλ
    1.72
    ônica
    1.71
    ؏
    1.71
    纔
    1.69
     merasakan
    1.69
     proizv
    1.67
    POSITIVE LOGITS
    £
    2.12
     £
    2.08
     Colours
    2.06
     Aluminium
    1.95
     alt
    1.95
     Online
    1.91
     aeroplane
    1.90
     polarisation
    1.90
     Página
    1.89
     armoured
    1.86
    Activations Density 0.011%

    No Known Activations