© 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. 175947
    Prev
    Next
    INDEX
    Explanations

    calling for explanations

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

    created by

    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
    appartement
    0.59
    y
    0.55
    yya
    0.53
    AX
    0.52
    yak
    0.52
    řad
    0.52
    コンピュー
    0.50
     تكبرها
    0.50
     会
    0.49
    icelli
    0.49
    POSITIVE LOGITS
    อ
    0.45
     नियंत्रण
    0.43
     Jahn
    0.43
     Johannes
    0.42
     postal
    0.42
    อะไร
    0.41
     szabály
    0.41
     trim
    0.40
     potassium
    0.39
     flue
    0.39
    Activations Density 0.000%

    No Known Activations