© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2133
    Prev
    Next
    INDEX
    Explanations

    professional responsibilities

    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
     along
    2.14
     an
    2.05
    some
    2.04
     disampaikan
    1.96
    unct
    1.96
     some
    1.90
     a
    1.90
     into
    1.89
     onto
    1.89
     with
    1.84
    POSITIVE LOGITS
    otrop
    2.67
    壹章
    2.49
    blest
    2.34
    第壹百
    2.33
    ʎ
    2.33
    <unused1874>
    2.32
     lugar
    2.29
    ahertz
    2.26
    icarbon
    2.24
    getImageFolder
    2.21
    Activations Density 0.128%

    No Known Activations