© 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. 222579
    Prev
    Next
    INDEX
    Explanations

    products and recommendations

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

    website links and portfolios

    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
    倠
    0.57
     我們
    0.56
     সিরিজের
    0.54
     heran
    0.53
    ீஸ்
    0.52
     серия
    0.51
    紗
    0.51
     waveform
    0.50
     za
    0.50
     ファン
    0.50
    POSITIVE LOGITS
    logout
    0.51
    spacerItem
    0.49
    dirs
    0.46
    Forbidden
    0.46
    ümü
    0.46
    business
    0.45
    canoe
    0.45
    )
    0.45
    Notifications
    0.44
    suspended
    0.44
    Activations Density 0.001%

    No Known Activations