© 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. 174397
    Prev
    Next
    INDEX
    Explanations

    finding words for or related to

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

    choose andchoose the

    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
    Goals
    0.51
    McC
    0.51
    ก
    0.50
    Cascade
    0.49
    ক
    0.48
    Measure
    0.46
    goals
    0.46
    Что
    0.45
    द
    0.45
    Ich
    0.45
    POSITIVE LOGITS
     parody
    0.46
     negatively
    0.44
     spoof
    0.44
     blogs
    0.43
     anonym
    0.42
     όμως
    0.42
     بعنوان
    0.42
     passports
    0.41
     unbearable
    0.41
     olmay
    0.41
    Activations Density 0.002%

    No Known Activations