© 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. 58543
    Prev
    Next
    INDEX
    Explanations

    subject to

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

    your permit

    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
     ఆలో
    0.38
    ],”
    0.38
     komplett
    0.38
    ത്തിയത്
    0.37
     విస్త
    0.37
     Retrieve
    0.36
    ilibr
    0.36
     steig
    0.36
    翀
    0.36
    oric
    0.36
    POSITIVE LOGITS
    緋
    0.46
    بی
    0.43
    อกาส
    0.43
    allowing
    0.42
    д
    0.42
    Bren
    0.42
    옷
    0.42
    ールの
    0.41
    restrictions
    0.41
    Wearing
    0.41
    Activations Density 0.000%

    No Known Activations