© 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. 31267
    Prev
    Next
    INDEX
    Explanations

    records from, tickets available, track race

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

    residue, simile, database, head, meme

    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
    ້ມ
    0.52
     reinforces
    0.50
    ຜະລິດຕະພັນ
    0.49
    хоро
    0.49
     qubits
    0.48
     menyiapkan
    0.48
    зий
    0.48
    ق
    0.47
     pion
    0.47
    нус
    0.46
    POSITIVE LOGITS
    !
    0.45
     Speed
    0.44
    NIH
    0.42
    ktionen
    0.42
     Baru
    0.41
    abhäng
    0.41
    IN
    0.41
     المع
    0.41
    ACTIV
    0.41
    Happy
    0.40
    Activations Density 0.000%

    No Known Activations