© 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. 73876
    Prev
    Next
    INDEX
    Explanations

    particulars, arresting, loss

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

    not and nor

    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
    说过
    0.45
     (<
    0.40
    misc
    0.40
    曩
    0.40
    wal
    0.39
     некоторые
    0.39
    rian
    0.39
     மற்றும்
    0.39
     وكذلك
    0.39
    orul
    0.39
    POSITIVE LOGITS
     removes
    0.50
     muszą
    0.48
     quantités
    0.47
     trzeba
    0.46
    Remove
    0.46
     unfolds
    0.45
     menyimpan
    0.45
     трябва
    0.44
    🏕
    0.44
    ໃຊ້
    0.44
    Activations Density 0.004%

    No Known Activations