© 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. 2668
    Prev
    Next
    INDEX
    Explanations

    counting numbers and words

    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
     organisers
    2.51
    佢
    2.31
     historians
    2.24
    فير
    2.23
    ungannya
    2.23
    真是
    2.22
    hoea
    2.19
    жении
    2.17
     Arrows
    2.14
     favourites
    2.13
    POSITIVE LOGITS
    7
    3.19
    8
    3.04
    rinsic
    2.96
    6
    2.75
    5
    2.65
    ຖານ
    2.63
     combust
    2.60
     perceiving
    2.56
    3
    2.46
     fizik
    2.42
    Activations Density 0.347%

    No Known Activations