© 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. 6970
    Prev
    Next
    INDEX
    Explanations

    goal accomplishment instructions

    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
     to
    0.75
     is
    0.70
    }.
    0.64
     was
    0.63
     and
    0.61
    يل
    0.61
     kaleidoscopic
    0.59
     on
    0.59
     kaleidoscope
    0.59
    },
    0.58
    POSITIVE LOGITS
    ও
    0.59
    ারে
    0.59
    ้อย
    0.58
    тят
    0.58
    ্যার
    0.57
    ıyorum
    0.54
    orragie
    0.54
    ın
    0.53
    डला
    0.52
    ﻑ
    0.52
    Activations Density 0.055%

    No Known Activations