© 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. 195059
    Prev
    Next
    INDEX
    Explanations

    personal pronoun followed by verb or noun

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

    generally, described, growing

    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
     ontstaan
    0.54
    ającą
    0.52
     expansión
    0.51
     geworden
    0.50
    संबंध
    0.50
    mäß
    0.50
    饨
    0.50
    áctica
    0.49
     wobec
    0.49
     борь
    0.49
    POSITIVE LOGITS
    AVG
    0.42
     blushed
    0.42
    セ
    0.42
    修
    0.42
    and
    0.42
    <0xE3>
    0.41
    no
    0.40
     sighed
    0.40
    ORE
    0.40
    Avg
    0.40
    Activations Density 0.000%

    No Known Activations