© 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. 31-GEMMASCOPE-2-RES-262K
    7. 47353
    Prev
    Next
    INDEX
    Explanations

    Finn was, can do, half looks

    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
    eb
    0.55
     weighty
    0.55
    hands
    0.50
    eg
    0.49
     coveted
    0.49
    e
    0.49
    charged
    0.49
    headed
    0.47
     discretionary
    0.47
     hands
    0.47
    POSITIVE LOGITS
     bactéries
    0.46
     Ihnen
    0.45
    鋆
    0.45
     treo
    0.44
    퐫
    0.44
     Even
    0.43
     PACK
    0.43
     principali
    0.42
     actores
    0.42
     মসজি
    0.41
    Activations Density 0.001%

    No Known Activations