© 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. 6775
    Prev
    Next
    INDEX
    Explanations

    or options

    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
    hesion
    0.36
    createdAt
    0.36
    VEN
    0.35
    USING
    0.35
    τηση
    0.34
    Roasted
    0.34
    κο
    0.33
    ᾧ
    0.33
    coupling
    0.33
    ORDAN
    0.32
    POSITIVE LOGITS
     cualquier
    0.50
     qualquer
    0.49
     कोणत्याही
    0.48
     herhangi
    0.47
     gült
    0.47
     அல்லது
    0.47
     hoặc
    0.46
     cualquiera
    0.46
     Qualquer
    0.46
     किंवा
    0.46
    Activations Density 0.162%

    No Known Activations