© 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. 91600
    Prev
    Next
    INDEX
    Explanations

    word followed by specific word

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

    suggesting names or options

    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
    ence
    0.51
     zdol
    0.50
    揉
    0.47
    investment
    0.46
    哪怕
    0.46
    നാ
    0.46
    ance
    0.45
     minuto
    0.45
     bigli
    0.45
    able
    0.44
    POSITIVE LOGITS
    quetas
    0.49
     сестра
    0.48
     깊
    0.48
     విజయ
    0.47
    Rafael
    0.45
     గు
    0.44
     јо
    0.44
     பிரதி
    0.43
     ге
    0.42
     HF
    0.42
    Activations Density 0.001%

    No Known Activations