© 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. 31-GEMMASCOPE-2-RES-262K
    7. 91560
    Prev
    Next
    INDEX
    Explanations

    write statements or suggestions

    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_31_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
    𐱃
    0.48
    قاء
    0.48
     internacional
    0.47
     Ausdruck
    0.47
     internationales
    0.46
     internacionais
    0.46
    য়েড
    0.44
     Forschung
    0.44
    Begriff
    0.44
     Dienste
    0.44
    POSITIVE LOGITS
    อร์
    0.51
    asse
    0.46
    กิน
    0.44
    SP
    0.42
     surge
    0.42
    ถ
    0.41
    บ
    0.41
     کیسے
    0.41
    ด
    0.40
    issuer
    0.40
    Activations Density 0.006%

    No Known Activations