© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 122725
    Prev
    Next
    INDEX
    Explanations

    vendor registration forms

    np_acts-logits-general · gemini-2.5-flash-lite

    code components and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataFrame
    0.41
    JEE
    0.41
    दून
    0.40
    わからない
    0.39
    _'+
    0.38
    そのまま
    0.38
    कान
    0.38
     respaldo
    0.38
     contains
    0.37
    ங்கை
    0.37
    POSITIVE LOGITS
     olmak
    0.41
    这件事
    0.41
     என்பத
    0.40
     annet
    0.40
    ).[
    0.39
     ########.
    0.39
    橄
    0.39
     Conseil
    0.39
     считается
    0.38
     वग
    0.38
    Activations Density 0.005%

    No Known Activations