© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126948
    Prev
    Next
    INDEX
    Explanations

    discussing inadequacies and necessities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    is
    0.46
    流域
    0.44
    rinos
    0.42
    CTOR
    0.42
    invest
    0.40
    ___
    0.40
    Utah
    0.40
    arios
    0.39
    Ligações
    0.39
     puissance
    0.39
    POSITIVE LOGITS
     th
    0.48
     BT
    0.47
     bt
    0.45
     italien
    0.44
    DependentUpon
    0.44
     interni
    0.44
    ⇝
    0.43
     internes
    0.42
     ý
    0.42
     curling
    0.42
    Activations Density 0.004%

    No Known Activations