© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192459
    Prev
    Next
    INDEX
    Explanations

    trip and travel itinerary

    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_40_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
    atação
    0.46
    ('/:
    0.42
    replacement
    0.41
     undisturbed
    0.41
     Ahmed
    0.40
     Replacement
    0.39
     unobstructed
    0.38
     опреде
    0.38
     replacements
    0.38
    otal
    0.38
    POSITIVE LOGITS
    立体
    0.42
     transgress
    0.40
    Charged
    0.40
    charged
    0.39
    ParentElement
    0.39
    ):
    0.38
    pitch
    0.38
     softening
    0.38
    pitched
    0.37
    스러
    0.37
    Activations Density 0.000%

    No Known Activations