© 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. 181547
    Prev
    Next
    INDEX
    Explanations

    buying, ordering, or planning

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

    inherent willingness to please

    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
     nello
    0.44
    <unused1068>
    0.44
     consecutively
    0.42
    haha
    0.42
     করেছে
    0.41
     במ
    0.41
    vice
    0.41
    nder
    0.41
    𝗂
    0.41
    cuts
    0.40
    POSITIVE LOGITS
     अस्थ
    0.42
     glucocortic
    0.42
     lanceol
    0.41
     অবধি
    0.41
     splenic
    0.40
    中止
    0.39
     আশায়
    0.39
     صحبت
    0.39
    ൊന്നും
    0.39
    GRANTED
    0.38
    Activations Density 0.000%

    No Known Activations