© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138046
    Prev
    Next
    INDEX
    Explanations

    fantasy, sci-fi, or numbers

    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_31_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
    (
    0.48
    en
    0.44
     veiled
    0.44
    }$-(
    0.43
     relatable
    0.43
    數字
    0.42
    }),
    0.41
     culpable
    0.41
    మ్
    0.41
    ї
    0.41
    POSITIVE LOGITS
     빅뱅
    0.44
    ophosph
    0.42
     pressur
    0.41
     Fiesta
    0.40
    旧
    0.40
     phishing
    0.38
    တွေ့
    0.38
     uno
    0.38
     palju
    0.38
     பழைய
    0.38
    Activations Density 0.008%

    No Known Activations