© 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. 220534
    Prev
    Next
    INDEX
    Explanations

    open or close

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

    work asmanager ofIS-ISBlackwoodwould think150; Marchdensity

    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
    {\
    0.47
     indicato
    0.44
    "
    0.43
    의
    0.43
     gameplay
    0.41
    ضح
    0.41
    bytecode
    0.40
    Accounts
    0.40
    Gameplay
    0.40
    र्
    0.40
    POSITIVE LOGITS
     Moreau
    0.52
     Antrag
    0.49
    TreeNavigator
    0.48
     braucht
    0.47
     Knoten
    0.46
     Votes
    0.46
     eignet
    0.46
     冖
    0.45
     måste
    0.44
     flexibilidad
    0.44
    Activations Density 0.001%

    No Known Activations