© 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. 124453
    Prev
    Next
    INDEX
    Explanations

    movement and progression

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

    responsibility and silence

    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
    }.
    0.47
    *.
    0.45
     omitted
    0.44
    }}$.
    0.43
    }.$
    0.43
     rú
    0.43
    ír
    0.43
    通风
    0.42
    **.
    0.42
    rufen
    0.42
    POSITIVE LOGITS
    ם
    0.45
    pressure
    0.43
     careful
    0.42
     cooperative
    0.42
     근무
    0.41
     入り
    0.41
     biotechnology
    0.41
     prosec
    0.40
     policing
    0.40
     campground
    0.40
    Activations Density 0.001%

    No Known Activations