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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41830
    Prev
    Next
    INDEX
    Explanations

    Bard, CPU, town

    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
     хотят
    0.45
    ilecek
    0.44
     willen
    0.43
    iziert
    0.43
     সময়ে
    0.42
     കെ
    0.42
    𝐃
    0.42
     forment
    0.42
    कि
    0.42
     obrigado
    0.42
    POSITIVE LOGITS
     decimals
    0.45
     دوسرا
    0.45
     TikTok
    0.45
     һәм
    0.44
     selfies
    0.44
    మ్
    0.42
    Anast
    0.42
     tassels
    0.41
     и
    0.41
     leaflets
    0.41
    Activations Density 0.009%

    No Known Activations