© 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-65K
    7. 50316
    Prev
    Next
    INDEX
    Explanations

    vapor and liquid phases

    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_65k_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
     Sejam
    0.47
     ච
    0.43
    lblCredits
    0.42
     Exile
    0.42
    deployRoot
    0.40
    ྤ
    0.40
    Ⴎ
    0.39
    LuaPush
    0.39
     namani
    0.39
    ெல்லி
    0.39
    POSITIVE LOGITS
    wood
    0.41
    ady
    0.41
     ginger
    0.39
     will
    0.38
     beating
    0.38
    ler
    0.36
    ginger
    0.36
    래
    0.35
    will
    0.35
     footing
    0.35
    Activations Density 0.001%

    No Known Activations