© 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. 2723
    Prev
    Next
    INDEX
    Explanations

    New companies, GPT transfer, Almorox

    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
     solvers
    1.26
     homepage
    1.26
     spelling
    1.25
     site
    1.24
     Vim
    1.24
     Tipp
    1.20
     yarns
    1.19
    ’
    1.19
     writes
    1.18
     Vicar
    1.18
    POSITIVE LOGITS
    8
    1.39
    7
    1.34
    udara
    1.33
    9
    1.33
    6
    1.25
    鈴
    1.23
    ٨
    1.22
    هایت
    1.21
    煖
    1.19
    ルフ
    1.19
    Activations Density 0.242%

    No Known Activations