© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28130
    Prev
    Next
    INDEX
    Explanations

    . or punctuation followed by word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indistinct
    0.37
     adoration
    0.37
     Estrella
    0.37
     $+$
    0.36
     adore
    0.36
     到
    0.36
    sebastian
    0.36
    rano
    0.36
     Bouquet
    0.36
     NavigationView
    0.35
    POSITIVE LOGITS
    ঙে
    0.38
    ፈር
    0.38
    ᠴ
    0.38
    acement
    0.37
    chym
    0.37
    breeds
    0.37
    лектро
    0.36
     ritmo
    0.36
    ლება
    0.36
    Bren
    0.36
    Activations Density 0.000%

    No Known Activations