© 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. 40-GEMMASCOPE-2-RES-262K
    7. 132155
    Prev
    Next
    INDEX
    Explanations

    vaadin

    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_40_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
    έσ
    0.44
    威尔
    0.38
    തന്ത്ര
    0.38
     repurchase
    0.36
     Smit
    0.36
    ilib
    0.35
     reconfiguration
    0.35
    繁
    0.35
    ulk
    0.35
    بات
    0.34
    POSITIVE LOGITS
    τέρα
    0.41
     Wagon
    0.40
    နေ
    0.39
     PN
    0.38
     Productions
    0.38
     دان
    0.38
    dan
    0.37
    {@
    0.37
    Productions
    0.37
    colas
    0.36
    Activations Density 0.004%

    No Known Activations