© 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. 58797
    Prev
    Next
    INDEX
    Explanations

    books versus

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

    common word pairings and endings

    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
    表演
    0.48
     cuz
    0.47
    '],'
    0.47
    溏
    0.43
     Donations
    0.42
    ),]$
    0.41
    ]}'
    0.40
     השי
    0.40
    邬
    0.40
     OKC
    0.40
    POSITIVE LOGITS
    larınız
    0.46
    trajectory
    0.45
    resource
    0.45
    sensitive
    0.43
    ტორი
    0.43
    requis
    0.42
    reasonable
    0.42
    criterion
    0.41
    readable
    0.41
    coll
    0.41
    Activations Density 0.000%

    No Known Activations