© 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. 3157
    Prev
    Next
    INDEX
    Explanations

    objectives, accomplishments, development

    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
    7
    1.55
    6
    1.38
    RIK
    1.37
    3
    1.33
    1
    1.33
    Creat
    1.29
    mono
    1.26
    DBO
    1.25
     cardiomyocytes
    1.24
     Rik
    1.24
    POSITIVE LOGITS
     vaccin
    1.28
    偕
    1.24
    Ela
    1.24
     Elles
    1.19
     euch
    1.18
    囝
    1.17
    ユー
    1.16
     Eust
    1.16
     quotation
    1.16
     מב
    1.14
    Activations Density 0.051%

    No Known Activations