© 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-65K
    7. 9784
    Prev
    Next
    INDEX
    Explanations

    border-radius and spacing

    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_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
     recesses
    0.40
     ou
    0.39
     robot
    0.39
     method
    0.39
     free
    0.39
     aks
    0.39
     u
    0.38
    鱔
    0.38
     output
    0.38
     jokes
    0.38
    POSITIVE LOGITS
    धि
    0.45
    𒈬
    0.44
    Corners
    0.44
    цаў
    0.43
     stood
    0.42
    єм
    0.42
    庵
    0.42
    ajati
    0.41
    Subgraph
    0.41
    Joined
    0.41
    Activations Density 0.028%

    No Known Activations