© 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. 110958
    Prev
    Next
    INDEX
    Explanations

    gift box

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

    Australian Jelly Bush honeys

    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
    atief
    0.46
     Mythology
    0.45
    有一定的
    0.44
     unordered
    0.42
     уту
    0.41
     transferencia
    0.41
    راءة
    0.41
    ]<?
    0.41
    atts
    0.40
    avec
    0.40
    POSITIVE LOGITS
    skar
    0.47
    त्मा
    0.45
     सर्वात
    0.45
    kel
    0.45
    keb
    0.44
    kos
    0.44
     डि
    0.43
     Cahill
    0.43
    matric
    0.42
    ibat
    0.42
    Activations Density 0.001%

    No Known Activations