© 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. 63266
    Prev
    Next
    INDEX
    Explanations

    biological or collapse

    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
    रुण
    0.50
    枪
    0.47
     choreographer
    0.47
     greasy
    0.46
    Бо
    0.44
     metaphorical
    0.44
     grease
    0.42
     PublicKey
    0.41
    ເພດ
    0.41
    ພວກເຮົາ
    0.41
    POSITIVE LOGITS
     dvs
    0.56
    ত্রের
    0.52
    enl
    0.51
    }$.
    0.51
    仳
    0.50
     koh
    0.50
    рад
    0.49
     ليس
    0.49
    )}$
    0.48
     nejsou
    0.48
    Activations Density 0.004%

    No Known Activations