© 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. 2750
    Prev
    Next
    INDEX
    Explanations

    sound and voices

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

    sound and noise

    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
    縝
    0.44
     उबर
    0.43
    紆
    0.42
     рациона
    0.41
     преступ
    0.40
     ITEMS
    0.40
     जोख
    0.39
     फुलकारी
    0.39
    衛
    0.39
     मानवता
    0.39
    POSITIVE LOGITS
     louder
    1.21
     loudness
    1.20
     audible
    1.16
     noise
    1.16
     dźwię
    1.16
     sound
    1.14
     loud
    1.14
     loudest
    1.14
    声音
    1.13
     zvuk
    1.13
    Activations Density 0.474%

    No Known Activations