© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3230
    Prev
    Next
    INDEX
    Explanations

    Keycloak login Western elites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    的很
    1.33
    isocyanate
    1.28
    gın
    1.24
    悉
    1.18
    高达
    1.17
     interi
    1.15
     zeroes
    1.14
     Bilingual
    1.13
     trillions
    1.12
     pequ
    1.11
    POSITIVE LOGITS
    θ
    1.29
     GTS
    1.25
     БД
    1.20
     STS
    1.14
    RP
    1.13
    Saw
    1.13
    gd
    1.12
    Kay
    1.11
    logs
    1.10
    GD
    1.10
    Activations Density 0.024%

    No Known Activations