© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127290
    Prev
    Next
    INDEX
    Explanations

    when, whenever, if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    Nombre
    0.52
     NOMBRE
    0.48
    GUND
    0.46
     ouvertes
    0.45
    Klas
    0.45
    
    0.44
    촤
    0.44
    雩
    0.44
    Magenta
    0.44
    nombre
    0.43
    POSITIVE LOGITS
     satisfying
    0.44
     whenever
    0.38
     When
    0.38
     Take
    0.37
     όταν
    0.37
     when
    0.36
     fórmulas
    0.36
     take
    0.36
     formula
    0.36
     Whenever
    0.36
    Activations Density 0.023%

    No Known Activations