© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217707
    Prev
    Next
    INDEX
    Explanations

    garden, activity, class

    np_acts-logits-general · gemini-2.5-flash-lite

    block address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𒁾
    0.53
    貳
    0.53
     अमाउंट
    0.51
     vadati
    0.50
     dvoj
    0.48
     sele
    0.48
     neko
    0.48
     saddhim
    0.48
     kontroll
    0.48
     vacanam
    0.48
    POSITIVE LOGITS
    ه
    0.52
    groupId
    0.51
    !==
    0.45
    ي
    0.45
     pierced
    0.45
    arch
    0.43
    بالإنجليزية
    0.43
    ศ
    0.42
    <0x9E>
    0.42
    ้
    0.41
    Activations Density 0.001%

    No Known Activations