© 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. 40-GEMMASCOPE-2-RES-262K
    7. 22109
    Prev
    Next
    INDEX
    Explanations

    marshmallow campfire stories

    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
    擇
    0.43
     убор
    0.41
     ylabel
    0.39
     Valves
    0.39
    ('.')[
    0.39
     energet
    0.38
    ান্দ
    0.38
    娼
    0.38
    quinazolin
    0.37
    orbid
    0.36
    POSITIVE LOGITS
     marshmallows
    1.43
     marshmallow
    1.27
     marshm
    1.11
    Marsh
    1.07
     Marsh
    1.05
    marsh
    0.94
     marsh
    0.93
     roasting
    0.88
     roasted
    0.80
     campfire
    0.78
    Activations Density 0.007%

    No Known Activations