© 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. 69850
    Prev
    Next
    INDEX
    Explanations

    Now that

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

    fidelity has, sense of, love and

    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
     fucking
    0.47
    ,
    0.46
    et
    0.45
     '
    0.44
     shirt
    0.43
     Broadway
    0.43
     barbec
    0.43
    akespe
    0.40
    င
    0.40
    गुण
    0.40
    POSITIVE LOGITS
    ONEDB
    0.57
    ордина
    0.50
     iskust
    0.50
    Melitaea
    0.50
     フォ
    0.47
     Aruba
    0.46
     gamanam
    0.46
     について
    0.46
    愘
    0.46
    ۹
    0.46
    Activations Density 0.001%

    No Known Activations