© 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. 132320
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases

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

    specific phrases of definition or quantity

    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
     thug
    0.49
    ங்கிணை
    0.44
    ཙ
    0.43
     cultures
    0.41
     torus
    0.40
     hermit
    0.40
     soluble
    0.40
     எதி
    0.40
     perg
    0.40
     culturas
    0.39
    POSITIVE LOGITS
    ه
    0.53
     поможет
    0.50
     Rey
    0.45
     Subject
    0.45
    tke
    0.44
     يساعد
    0.44
    াইব
    0.44
    AR
    0.43
    stvo
    0.43
    ৬০
    0.42
    Activations Density 0.001%

    No Known Activations