© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3456
    Prev
    Next
    INDEX
    Explanations

    need not

    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_16_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
     to
    0.67
    1
    0.66
     A
    0.61
     area
    0.59
     ISS
    0.59
    0
    0.59
     and
    0.59
     IC
    0.59
     or
    0.59
     P
    0.58
    POSITIVE LOGITS
    of
    0.57
     praktisch
    0.55
     schön
    0.55
     nemus
    0.54
     schönsten
    0.50
    時尚
    0.50
     höch
    0.49
    sebastian
    0.49
    א
    0.49
    beautiful
    0.49
    Activations Density 0.000%

    No Known Activations