© 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-16K
    7. 12702
    Prev
    Next
    INDEX
    Explanations

    Micro-LED Display

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

    emojis and non-english scripts

    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_16k_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
    0.50
    ’
    0.47
    and
    0.45
    ot
    0.42
    wdir
    0.42
    amp
    0.40
    pub
    0.40
    g
    0.39
     micros
    0.39
    art
    0.38
    POSITIVE LOGITS
    ුණු
    0.42
     言っ
    0.41
     rừng
    0.40
     തുട
    0.40
    高兴
    0.40
    🙄
    0.38
     ところ
    0.38
     መሳሪያ
    0.37
    பாய்
    0.37
     વિચારો
    0.37
    Activations Density 0.205%

    No Known Activations