© 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. 34137
    Prev
    Next
    INDEX
    Explanations

    forms of 'to be' 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-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
     presentes
    0.46
    S
    0.44
    interested
    0.42
     prêts
    0.40
    tied
    0.39
    Collapsed
    0.39
    Flore
    0.39
     disponibles
    0.39
    concerned
    0.39
    들
    0.39
    POSITIVE LOGITS
     capaz
    0.54
     motivo
    0.43
     possível
    0.42
    queleto
    0.41
     válido
    0.41
     infatti
    0.40
     uma
    0.40
     capazes
    0.39
     preciso
    0.39
     noticia
    0.38
    Activations Density 0.013%

    No Known Activations