© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159928
    Prev
    Next
    INDEX
    Explanations

    Party Offer, conversion numbers

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

    identifying specific context

    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
    زع
    0.52
    ánea
    0.52
    袈
    0.50
    タリア
    0.47
    زب
    0.45
     Enemies
    0.45
    𝒌
    0.45
    禳
    0.44
     Ressources
    0.44
    クトル
    0.44
    POSITIVE LOGITS
    8
    0.50
    6
    0.46
    2
    0.44
     adapter
    0.40
    7
    0.40
     bonded
    0.39
     disampaikan
    0.39
    4
    0.39
     conveying
    0.38
    9
    0.38
    Activations Density 0.001%

    No Known Activations