© 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. 62767
    Prev
    Next
    INDEX
    Explanations

    months and days

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

    theories of punishment, incorrect proof

    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
    batch
    0.44
    Batch
    0.44
    an
    0.44
    ist
    0.44
    ਰ
    0.43
    ay
    0.42
    atch
    0.42
    awake
    0.41
    Thing
    0.41
    ing
    0.41
    POSITIVE LOGITS
     dobbiamo
    0.47
     武田
    0.47
     پایان
    0.46
    ത്തിലേക്ക്
    0.46
     callSettings
    0.45
     秦
    0.44
     赵
    0.44
     życia
    0.44
     HUMAN
    0.43
     consecuencias
    0.43
    Activations Density 0.000%

    No Known Activations