© 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. 238874
    Prev
    Next
    INDEX
    Explanations

    acts on input or asks for information

    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
     کي
    0.50
     کال
    0.48
     ब
    0.46
     bors
    0.46
     остаются
    0.46
     indemnify
    0.46
     chcia
    0.45
     знали
    0.45
    arlal
    0.45
     были
    0.44
    POSITIVE LOGITS
    ה
    0.50
    matter
    0.50
     Vaccine
    0.48
    ת
    0.48
    v
    0.47
    т
    0.47
    nieuw
    0.46
    璞
    0.45
    pun
    0.45
     ensuite
    0.45
    Activations Density 0.000%

    No Known Activations