© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56085
    Prev
    Next
    INDEX
    Explanations

    protecting children

    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
     thio
    0.50
     коюм
    0.49
     delito
    0.46
    ើញ
    0.46
    هو
    0.46
     голова
    0.46
    ುದು
    0.45
    ̝
    0.44
     bào
    0.44
    ﻞ
    0.44
    POSITIVE LOGITS
    resses
    0.50
     biograf
    0.45
    实现
    0.44
     carrera
    0.43
     advers
    0.41
     brillantes
    0.41
     sensations
    0.41
     artistes
    0.40
    ską
    0.40
     auteurs
    0.40
    Activations Density 0.003%

    No Known Activations