© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 121477
    Prev
    Next
    INDEX
    Explanations

    legal or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    fictional scenarios and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    0.58
    ar
    0.47
    amen
    0.45
    arjo
    0.42
    arle
    0.42
    че
    0.40
    rith
    0.40
    }]
    0.40
    addKill
    0.40
    meny
    0.40
    POSITIVE LOGITS
     pinched
    0.43
     knuckle
    0.43
     phoenix
    0.42
     Husky
    0.42
     ce
    0.41
    砕
    0.41
     spacer
    0.40
     Pfer
    0.40
     Unicorn
    0.39
     Femme
    0.39
    Activations Density 0.001%

    No Known Activations