© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77137
    Prev
    Next
    INDEX
    Explanations

    will take

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    報
    0.50
    Credentials
    0.50
    Յ
    0.47
    ճ
    0.47
    пе
    0.46
    貿易
    0.46
    難
    0.46
    活
    0.46
    レベル
    0.45
    ាត់
    0.44
    POSITIVE LOGITS
     the
    0.64
     Ltd
    0.49
    arın
    0.47
     incontinence
    0.47
     endoscopic
    0.47
     its
    0.46
     kayak
    0.45
     Godzilla
    0.45
     desconocido
    0.44
     посмотрим
    0.44
    Activations Density 0.007%

    No Known Activations