© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 6806
    Prev
    Next
    INDEX
    Explanations

    compound interest, reading, building material

    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_16_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
    防
    0.51
     vehement
    0.47
     hardy
    0.44
    ဴ
    0.44
     connector
    0.44
     toluene
    0.43
     cracking
    0.41
     бло
    0.41
    க்கூ
    0.40
     cursory
    0.40
    POSITIVE LOGITS
    agnes
    0.53
    sinya
    0.51
    ).
    0.51
    imagem
    0.50
     infert
    0.50
    ).</
    0.50
     ReturnVal
    0.48
    ott
    0.47
    aternity
    0.47
    ?).
    0.47
    Activations Density 0.000%

    No Known Activations