© 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. 84656
    Prev
    Next
    INDEX
    Explanations

    painting and home improvement

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

    lack of understanding or tracking

    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
    았던
    0.47
    െ
    0.44
    érations
    0.42
    Yr
    0.42
    ומי
    0.42
    이었
    0.41
    ар
    0.40
     ions
    0.40
    톡
    0.40
     activités
    0.39
    POSITIVE LOGITS
    )^{(
    0.50
    neus
    0.47
    JECT
    0.46
     कब्रिस्तान
    0.45
    AKE
    0.45
    荥
    0.45
     kaos
    0.44
    il
    0.44
     चुना
    0.44
    timeslots
    0.43
    Activations Density 0.002%

    No Known Activations