© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54357
    Prev
    Next
    INDEX
    Explanations

    increase or elevate

    np_acts-logits-general · gemini-2.5-flash-lite

    get to the other side

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ami
    0.48
    ocou
    0.47
    :
    0.46
    ،
    0.44
    і
    0.44
    ology
    0.43
     Radcliffe
    0.43
     Riverside
    0.43
    Bou
    0.43
    യു
    0.42
    POSITIVE LOGITS
     incremento
    0.57
     incrementar
    0.53
     увеличения
    0.52
     demás
    0.50
    岕
    0.50
     elevar
    0.50
     aumentare
    0.49
     messo
    0.49
     bauen
    0.48
     elevate
    0.48
    Activations Density 0.000%

    No Known Activations