© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19475
    Prev
    Next
    INDEX
    Explanations

    code identifiers and results

    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
     siè
    0.46
     strictly
    0.43
     by
    0.41
     fence
    0.40
     with
    0.39
     valve
    0.39
     ----------
    0.38
    యే
    0.38
     justice
    0.38
     passage
    0.38
    POSITIVE LOGITS
     название
    0.49
     этому
    0.48
    он
    0.46
     اسم
    0.42
     її
    0.42
     оно
    0.41
    ٩
    0.41
     أيضاً
    0.40
     namn
    0.39
    ätt
    0.39
    Activations Density 0.001%

    No Known Activations