© 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. 138890
    Prev
    Next
    INDEX
    Explanations

    preserving our

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

    programming, APIs, and datasets

    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
     baza
    0.53
    墺
    0.49
     solicitar
    0.48
     zespołu
    0.48
     prakt
    0.48
     predecess
    0.47
     humanist
    0.47
     seminary
    0.47
     dünyanın
    0.47
     chefs
    0.46
    POSITIVE LOGITS
    9
    0.47
    ^{*}$
    0.45
    рти
    0.45
    8
    0.44
    mr
    0.42
    which
    0.42
    1
    0.42
    ]
    0.41
    {~
    0.41
    mh
    0.40
    Activations Density 0.000%

    No Known Activations