© 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. 142248
    Prev
    Next
    INDEX
    Explanations

    star-forming regions and economic phases

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

    listing on, integration with, archived memories, understanding female

    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
    ninja
    0.59
     välja
    0.53
    らず
    0.51
     खांसी
    0.51
     なさい
    0.50
    biti
    0.50
     由
    0.49
    nije
    0.47
     izaz
    0.47
     DENUMIRE
    0.47
    POSITIVE LOGITS
    ές
    0.46
     executed
    0.44
    지요
    0.44
     RIM
    0.43
    ય
    0.43
     aux
    0.42
     factory
    0.41
    ків
    0.41
     phases
    0.40
     уго
    0.40
    Activations Density 0.000%

    No Known Activations