© 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-65K
    7. 50450
    Prev
    Next
    INDEX
    Explanations

    define what or defenses

    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_65k_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
     comenzó
    0.44
     explosives
    0.44
     बड़े
    0.43
     mascotas
    0.42
    ╧
    0.42
     मोठा
    0.42
     unexpected
    0.42
     comenzaron
    0.42
    एयर
    0.41
    ίος
    0.41
    POSITIVE LOGITS
     oeuvre
    0.52
     کوشش
    0.47
     არს
    0.45
     Bourd
    0.45
     Christendom
    0.45
    缤
    0.44
     quatro
    0.42
     നമു
    0.42
    踽
    0.42
     Cuerpo
    0.41
    Activations Density 0.027%

    No Known Activations