© 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. 40-GEMMASCOPE-2-RES-262K
    7. 32781
    Prev
    Next
    INDEX
    Explanations

    somewhere or sometime

    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_40_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
     Make
    0.47
     Others
    0.45
     Vent
    0.45
     Fe
    0.45
     जरा
    0.44
     For
    0.44
     (<
    0.44
     HX
    0.43
     Both
    0.42
     V
    0.42
    POSITIVE LOGITS
     somewhere
    0.88
     irgendwo
    0.78
     Somewhere
    0.70
     someplace
    0.69
    Somewhere
    0.69
     tussen
    0.66
     между
    0.65
     giữa
    0.64
     between
    0.61
     pomiędzy
    0.59
    Activations Density 0.005%

    No Known Activations