© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    team members

    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
     strait
    1.63
    ágina
    1.52
     ophthal
    1.49
     Caul
    1.49
     dyslexia
    1.48
     ophthalm
    1.48
    ช่อง
    1.47
    게
    1.45
     rém
    1.44
    sul
    1.44
    POSITIVE LOGITS
     members
    3.23
     Members
    2.95
    成员
    2.91
     MEMBERS
    2.88
     member
    2.83
    成員
    2.80
     membri
    2.56
    Members
    2.54
    members
    2.53
    member
    2.52
    Activations Density 0.403%

    No Known Activations