© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9874
    Prev
    Next
    INDEX
    Explanations

    Mighty followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite

    Mighty Rio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Synt
    0.49
     synt
    0.45
    鞑
    0.45
     Mara
    0.43
     ничек
    0.43
    语法
    0.43
     Syntax
    0.42
     شیع
    0.42
     Elemente
    0.42
     syntactic
    0.42
    POSITIVE LOGITS
    hbar
    0.48
    scient
    0.44
    ℏ
    0.43
    raphene
    0.43
    modulation
    0.42
    however
    0.41
    hue
    0.41
    scientist
    0.40
    scientific
    0.40
    conservation
    0.40
    Activations Density 0.002%

    No Known Activations