© 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. 31-GEMMASCOPE-2-RES-262K
    7. 10860
    Prev
    Next
    INDEX
    Explanations

    abstract qualities and positive states

    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
    ↵
    0.60
     T
    0.56
     unofficial
    0.51
     B
    0.51
     s
    0.50
    /
    0.50
    h
    0.50
     S
    0.50
    u
    0.49
    ts
    0.49
    POSITIVE LOGITS
     maravilloso
    0.66
     meravigli
    0.62
    美丽的
    0.61
     maravill
    0.59
    鲞
    0.59
    怎样的
    0.58
     prachtige
    0.57
    美丽
    0.57
    这样的
    0.55
    生命的
    0.55
    Activations Density 0.029%

    No Known Activations