© 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. 3048
    Prev
    Next
    INDEX
    Explanations

    chatbot models

    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
    2.13
    9
    2.01
    8
    2.00
    6
    1.93
    5
    1.85
    4
    1.72
    3
    1.67
    0
    1.47
    1
    1.41
    rinsic
    1.35
    POSITIVE LOGITS
     Ramb
    1.62
    𝒓
    1.46
     (£
    1.44
    タック
    1.39
     taut
    1.39
    她在
    1.39
    hoea
    1.36
    囝
    1.34
    šit
    1.33
    orter
    1.33
    Activations Density 0.035%

    No Known Activations