© 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. 186163
    Prev
    Next
    INDEX
    Explanations

    laws, applications, crisis, selfie

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

    fine-tuned models

    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
    HOW
    0.53
    IM
    0.49
    MORD
    0.49
    红
    0.48
    紅
    0.46
    व
    0.46
    مر
    0.46
    IE
    0.45
    CLUB
    0.45
    ↵
    0.45
    POSITIVE LOGITS
     sized
    0.49
     ফেরত
    0.47
    ikus
    0.47
     እድ
    0.46
     sleeveless
    0.44
     사이즈
    0.43
     размера
    0.42
     गोयल
    0.42
     geometrically
    0.42
     Incidentally
    0.41
    Activations Density 0.001%

    No Known Activations