© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 547
    Prev
    Next
    INDEX
    Explanations

    style, maintenance, decryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     organisers
    1.83
     historians
    1.82
    タック
    1.80
     Vee
    1.68
     predictions
    1.68
    スケジュール
    1.63
    スの
    1.59
    𝗸
    1.58
     considers
    1.56
     cruises
    1.56
    POSITIVE LOGITS
    rinsic
    1.74
    Diffuse
    1.67
    9
    1.63
     makeSound
    1.60
    7
    1.60
    º
    1.56
    mean
    1.52
    торое
    1.51
    6
    1.47
     mascul
    1.45
    Activations Density 0.196%

    No Known Activations