© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 120554
    Prev
    Next
    INDEX
    Explanations

    personal data and curriculum

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

    compound nouns and specific phrases

    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_31_width_262k_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
     elasticity
    0.48
     cómodo
    0.46
     prudence
    0.46
     thermometers
    0.46
     versatility
    0.45
     strongest
    0.45
    𝚒
    0.45
     plaus
    0.44
    Ty
    0.44
     sıcak
    0.44
    POSITIVE LOGITS
     Bef
    0.44
    Data
    0.43
    data
    0.41
    adari
    0.41
    onio
    0.40
    addling
    0.40
    荳
    0.40
    social
    0.40
    ⁵
    0.40
     be
    0.39
    Activations Density 0.002%

    No Known Activations