© 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. 32401
    Prev
    Next
    INDEX
    Explanations

    officials and spokespeople

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

    Lists with descriptions

    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
     agent
    0.46
     Pickup
    0.42
    ❂
    0.42
    dance
    0.41
     AISI
    0.41
     Watt
    0.41
     dug
    0.40
     agente
    0.40
     Rate
    0.40
    ابق
    0.40
    POSITIVE LOGITS
     ಪ್ರಶ್
    0.44
    𝔞
    0.44
     निवडणु
    0.44
     делу
    0.43
    私も
    0.43
    ことも
    0.42
    ISTIC
    0.42
     செய்யப்படும்
    0.42
    TISE
    0.42
    BP
    0.42
    Activations Density 0.001%

    No Known Activations