© 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. 134992
    Prev
    Next
    INDEX
    Explanations

    mobile applications and platforms

    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
    URNIZOR
    0.50
    髙
    0.47
    なら
    0.46
    かもしれない
    0.46
    Dangerous
    0.46
     δὲ
    0.45
     さらに
    0.45
    连锁
    0.45
    鉋
    0.45
    Ꮁ
    0.44
    POSITIVE LOGITS
     mobil
    0.53
     passcode
    0.50
     mobile
    0.50
     invincible
    0.50
     smartphone
    0.49
     hostels
    0.49
     platforms
    0.48
     immortal
    0.48
     App
    0.47
     platform
    0.46
    Activations Density 0.000%

    No Known Activations