© 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. 175467
    Prev
    Next
    INDEX
    Explanations

    vowel sounds and pronunciation

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

    phonetic sounds and articulation

    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
     店舗
    0.47
     indemnify
    0.44
     freelancers
    0.43
     dealerships
    0.43
     অনিবার্য
    0.43
     Цуки
    0.42
    뗑
    0.42
    衛星
    0.42
     retail
    0.42
    賖
    0.42
    POSITIVE LOGITS
     vowel
    0.88
     vowels
    0.83
     phon
    0.72
     phonetic
    0.71
     articul
    0.69
     音
    0.66
    phon
    0.65
     Phon
    0.64
    音
    0.64
     consonants
    0.63
    Activations Density 0.026%

    No Known Activations