© 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. 149606
    Prev
    Next
    INDEX
    Explanations

    immediate shore

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

    social media and internet presence

    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
    es
    0.50
    Cheng
    0.47
    Palm
    0.46
    ing
    0.46
    AppContext
    0.45
    Exe
    0.44
    journ
    0.44
    几
    0.44
    Mou
    0.44
    1
    0.43
    POSITIVE LOGITS
     نروح
    0.53
     znaleźć
    0.46
     onstage
    0.45
    ក៏
    0.45
    čí
    0.45
     aute
    0.45
     আস্থা
    0.45
     slammed
    0.45
     hotly
    0.45
     топлива
    0.45
    Activations Density 0.000%

    No Known Activations