© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2743
    Prev
    Next
    INDEX
    Explanations

    heights and lengths in feet and inches

    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
    舸
    0.46
     వె
    0.46
    鳌
    0.45
    搅拌
    0.45
    禳
    0.45
    巉
    0.43
    禊
    0.42
    لاسه
    0.41
    豇
    0.41
    含义
    0.41
    POSITIVE LOGITS
     antihy
    0.63
     hypertension
    0.63
     hypertensive
    0.56
     blood
    0.48
     arterial
    0.47
     medications
    0.46
     drugs
    0.46
     Hypertension
    0.45
     diuretics
    0.45
     angiotensin
    0.45
    Activations Density 0.001%

    No Known Activations