© 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. 126232
    Prev
    Next
    INDEX
    Explanations

    lists, descriptions, instructions

    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
     accelerates
    0.50
    .
    0.50
     unsurprisingly
    0.49
     argues
    0.49
     wasn
    0.49
    itra
    0.48
     கொடுத்து
    0.48
    ente
    0.47
     Зу
    0.47
     influencers
    0.46
    POSITIVE LOGITS
    р
    0.48
     کھیلنا
    0.47
    FOUND
    0.45
     kapal
    0.42
    فهام
    0.42
     pomoc
    0.42
    스로
    0.41
     v
    0.41
     déplacement
    0.41
    ങ്ങ്
    0.40
    Activations Density 0.003%

    No Known Activations