© 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. 4604
    Prev
    Next
    INDEX
    Explanations

    html title visible

    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
     torsional
    1.30
     synapses
    1.22
    тів
    1.15
    anooga
    1.14
    
    1.12
    latego
    1.11
    ATPase
    1.09
     Thomson
    1.09
    颱
    1.08
    Thom
    1.07
    POSITIVE LOGITS
    bes
    1.17
     different
    1.07
    いくつかの
    1.05
    lb
    1.04
     various
    1.04
    fg
    0.99
    let
    0.94
    be
    0.93
     عدة
    0.93
     Bd
    0.92
    Activations Density 0.033%

    No Known Activations