© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49736
    Prev
    Next
    INDEX
    Explanations

    default parameter values

    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_65k_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
    iga
    0.48
    is
    0.46
     வரி
    0.46
     default
    0.45
     ltd
    0.45
    ines
    0.44
    ties
    0.43
    ྨ
    0.43
    ۴
    0.42
     programación
    0.42
    POSITIVE LOGITS
    ReadAll
    0.42
    กาย
    0.42
    ريقيا
    0.41
    囪
    0.41
     extinguishing
    0.40
    鶴
    0.40
    Glucose
    0.39
    珩
    0.39
     écoul
    0.38
    ிருக்கிறது
    0.37
    Activations Density 0.001%

    No Known Activations