© 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-65K
    7. 54089
    Prev
    Next
    INDEX
    Explanations

    more than simply

    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
    YNAM
    0.48
    fia
    0.47
    衙
    0.46
    åg
    0.44
     राजवंश
    0.43
    ський
    0.43
    ству
    0.41
    ським
    0.41
    _',
    0.41
     DIFFICULTY
    0.41
    POSITIVE LOGITS
     optimism
    0.56
     novice
    0.53
     carefree
    0.53
     improvement
    0.50
     optimistic
    0.50
     hump
    0.49
     gender
    0.48
     caregivers
    0.48
     width
    0.47
     crisp
    0.47
    Activations Density 0.015%

    No Known Activations