© 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. 237034
    Prev
    Next
    INDEX
    Explanations

    common word pairings

    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
    ي
    0.49
    نون
    0.47
     đưa
    0.46
    نية
    0.46
     enrolling
    0.46
    يقة
    0.45
    \"]
    0.45
    \$
    0.44
    केर
    0.43
     sustained
    0.42
    POSITIVE LOGITS
     padding
    0.47
     письмо
    0.42
    สเตอร์
    0.42
    PATCH
    0.41
     cushion
    0.41
     रफी
    0.40
     trailer
    0.39
     putty
    0.39
     refurb
    0.38
    abyte
    0.38
    Activations Density 0.000%

    No Known Activations