© 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. 208398
    Prev
    Next
    INDEX
    Explanations

    building and landmark descriptions

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

    measuring how

    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
     prochain
    0.47
    E
    0.46
    S
    0.45
    Quarter
    0.45
     Tactics
    0.45
    Sprite
    0.44
    Descriptors
    0.44
    Nano
    0.43
    Jackson
    0.43
    प्तान
    0.43
    POSITIVE LOGITS
    squa
    0.46
    trusive
    0.46
    currentItem
    0.46
     ಬ
    0.46
    blusa
    0.44
     untrue
    0.43
    sqlUpdate
    0.43
    jsdel
    0.43
    ্া
    0.42
    addNew
    0.42
    Activations Density 0.000%

    No Known Activations