© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30254
    Prev
    Next
    INDEX
    Explanations

    less likely to switch

    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
     Harmonic
    0.46
    }$.)
    0.45
    ）。
    0.45
     Applying
    0.45
    tez
    0.44
     Withdrawal
    0.44
     Paths
    0.43
    tained
    0.42
    .)
    0.42
    )。
    0.42
    POSITIVE LOGITS
     quando
    0.50
    Cuando
    0.49
    ﺑ
    0.48
     digitally
    0.46
    ﻳ
    0.46
    \%$
    0.46
    Ketika
    0.46
    ﺿ
    0.44
    0
    0.43
    ço
    0.42
    Activations Density 0.001%

    No Known Activations