© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109758
    Prev
    Next
    INDEX
    Explanations

    electricity and gravity

    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
     enkel
    0.49
     божомол
    0.48
    partners
    0.48
    상은
    0.47
    상이
    0.46
    uddho
    0.46
    𝘴
    0.46
    coupled
    0.46
    accesso
    0.45
    }]\
    0.45
    POSITIVE LOGITS
     gravity
    0.53
     termination
    0.48
     battery
    0.48
     electric
    0.47
     batteria
    0.46
     restoration
    0.46
    ě
    0.46
     bateria
    0.46
     strobe
    0.45
     load
    0.45
    Activations Density 0.007%

    No Known Activations