© 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. 203927
    Prev
    Next
    INDEX
    Explanations

    question starters and qualifiers

    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
     mondial
    0.48
    a
    0.47
     camar
    0.45
    3
    0.45
     System
    0.44
     contabil
    0.44
    №
    0.43
     présent
    0.43
     Consult
    0.42
    、
    0.42
    POSITIVE LOGITS
    prechen
    0.50
    Pis
    0.47
    Waar
    0.46
    ivado
    0.46
     σχε
    0.45
    Khi
    0.45
     अति
    0.44
    itzen
    0.44
    itetty
    0.44
     Pharisees
    0.44
    Activations Density 0.003%

    No Known Activations