© 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. 64690
    Prev
    Next
    INDEX
    Explanations

    capture perfect, clear statements

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

    explaining transcription is

    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
    KS
    0.45
    0.45
    catering
    0.44
    NOV
    0.43
     Obr
    0.43
    Emotion
    0.43
    ONG
    0.42
    HOST
    0.42
    ⑶
    0.42
                           
    0.42
    POSITIVE LOGITS
     diantaranya
    0.46
     பொரு
    0.45
    ඃ
    0.45
    ishable
    0.44
    手数
    0.44
     daisies
    0.44
    ждение
    0.43
    ஞ்சம்
    0.43
    ণ্ডের
    0.42
    <0x91>
    0.42
    Activations Density 0.001%

    No Known Activations