© 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. 31-GEMMASCOPE-2-RES-262K
    7. 208380
    Prev
    Next
    INDEX
    Explanations

    possessive, whose, previous

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

    explains specific details or examples

    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
    ართ
    0.48
    ruits
    0.46
    ärm
    0.44
    箫
    0.44
     акты
    0.43
    ausea
    0.42
    ੪
    0.42
    美しい
    0.42
    音
    0.42
    yler
    0.42
    POSITIVE LOGITS
     cuyas
    0.58
     whose
    0.51
     cuya
    0.50
     cujo
    0.49
     zuvor
    0.46
     cuja
    0.46
     গিয়ে
    0.46
     cuyo
    0.46
     das
    0.45
     swojej
    0.45
    Activations Density 0.001%

    No Known Activations