© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50398
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and languages

    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
     R
    0.56
    a
    0.53
    and
    0.51
    an
    0.50
     N
    0.48
     B
    0.46
     Oculus
    0.45
     A
    0.45
     O
    0.44
    el
    0.43
    POSITIVE LOGITS
    ждает
    0.45
     toolPath
    0.41
     ہے
    0.41
     Gdy
    0.40
    റുണ്ട്
    0.40
    AZIONE
    0.40
     principalTable
    0.40
     Sebasti
    0.39
     CheckKey
    0.39
    녠
    0.39
    Activations Density 0.000%

    No Known Activations